© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12766
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making criteria and logical conditions.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statements that give conditional, second-person guidance for choosing between options based on situational factors and requirements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    conditional or situational guidance phrases, particularly those discussing when or under what circumstances to use different approaches or make decisions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mérito
    -0.32
     opty
    -0.30
     jupe
    -0.29
     dividido
    -0.28
    ar
    -0.28
     Baldwin
    -0.28
     hallaz
    -0.28
    englanniksi
    -0.28
     poziom
    -0.27
    不同
    -0.27
    POSITIVE LOGITS
     للاسماء
    0.71
    tagHelperRunner
    0.67
     AssemblyTitle
    0.67
    IsMutable
    0.67
     myſelf
    0.65
     pleaſure
    0.63
     AssemblyCulture
    0.59
    OGND
    0.58
    WriteBarrier
    0.57
    ToBounds
    0.57
    Activations Density 0.345%

    No Known Activations