© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8855
    Prev
    Next
    INDEX
    Explanations

    elements related to personal relationships and parenting

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

    following common nouns

    np_acts-logits-general · gemini-2.0-flash

    right vs privilege

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ViewImports
    -0.47
     verwij
    -0.42
    dear
    -0.39
    Pop
    -0.39
    Referencias
    -0.38
     aufzu
    -0.38
     referring
    -0.38
    hian
    -0.38
    ggia
    -0.38
     tardi
    -0.38
    POSITIVE LOGITS
    WriteTagHelper
    0.56
     HttpNotFound
    0.44
    Diweddarwch
    0.42
     ostavi
    0.41
     Exacts
    0.40
    exprimer
    0.39
    extAlignment
    0.38
    ::_('
    0.37
     ludzie
    0.36
     Numerade
    0.36
    Activations Density 0.411%

    No Known Activations