Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5212
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and caregiving dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    AsUp
    -0.58
     समीक्षक
    -0.47
     voet
    -0.44
    fjspx
    -0.42
    citenamefont
    -0.42
     gevo
    -0.41
     lijn
    -0.41
    Prí
    -0.41
     tabPage
    -0.40
     verwacht
    -0.40
    POSITIVE LOGITS
     covenants
    0.42
     صوتيه
    0.40
    __*/
    0.40
     comprends
    0.39
    Geografi
    0.38
    jsii
    0.37
    tagext
    0.36
    LayoutConstraint
    0.35
    lesias
    0.35
    reprodu
    0.35
    Activations Density 0.236%

    No Known Activations