© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5804
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making or evaluating options

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

    internal psychological struggles or moments of indecision.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    Дереккөздер
    -0.51
    OGND
    -0.49
     nationales
    -0.47
     Umgang
    -0.45
    ragalactic
    -0.45
    onomies
    -0.45
     cellars
    -0.45
    UrlResolution
    -0.43
     aberrations
    -0.43
     виправивши
    -0.42
    POSITIVE LOGITS
     decision
    0.65
    decision
    0.58
    ScopeManager
    0.52
     hesitation
    0.50
     DECISION
    0.48
    <?
    0.48
    AnchorStyles
    0.47
     Decision
    0.47
    AndEndTag
    0.47
     hes
    0.45
    Activations Density 0.187%

    No Known Activations