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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5213
    Prev
    Next
    INDEX
    Explanations

    calls to action for community participation and support

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

    persuasive language that encourages people to take action, like voting, donating, or joining an event.

    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
    XmlAccessType
    -0.63
    mappedBy
    -0.54
     للمعارف
    -0.54
    Bioaccumulative
    -0.53
     Bose
    -0.50
    AppMethodBeat
    -0.50
     iNdEx
    -0.48
    pencer
    -0.48
    Източници
    -0.48
    BeginInit
    -0.47
    POSITIVE LOGITS
    发表于
    0.42
    GOTREF
    0.40
     henkil
    0.35
     الحره
    0.33
    EDEFAULT
    0.32
     ajudá
    0.32
     either
    0.31
    สือ
    0.31
     odw
    0.30
     koniecz
    0.30
    Activations Density 0.115%

    No Known Activations