© 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. 15303
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to equations and inequalities

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

    mathematical expressions containing "n-1" or similar numerical sequences with subtraction.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    もしろ
    -0.51
    /**
    -0.47
    mpagne
    -0.47
    XmlSchema
    -0.47
    这件事情
    -0.46
    bibfield
    -0.45
    =".$
    -0.44
    bibinfo
    -0.44
    %%%%%%%%%%%%%%%%
    -0.44
    ſtre
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.44
    expandindo
    0.43
    audiovisuel
    0.43
    xFFFFFFFF
    0.41
     sebelumnya
    0.40
    oredCriteria
    0.40
    VersionUID
    0.40
    vados
    0.40
    RTSN
    0.40
    postsleuth
    0.39
    Activations Density 0.367%

    No Known Activations