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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15180
    Prev
    Next
    INDEX
    Explanations

    references to formal documents, clauses, or legal terms

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

    Comes after titles (Mr, Dr) and numbers

    np_acts-logits-general · gemini-2.0-flash

    reporting incidents

    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
    ArrowToggle
    -0.46
     ComVisible
    -0.42
    ResponseWriter
    -0.42
    principalColumn
    -0.40
    tagHelper
    -0.39
     AssemblyCulture
    -0.39
     Italijani
    -0.39
    +#+
    -0.38
    bitField
    -0.38
    Personendaten
    -0.38
    POSITIVE LOGITS
    findpost
    0.64
    NUMX
    0.49
    +#+#
    0.44
     otomatig
    0.44
     Carb
    0.44
    ScopeManager
    0.44
     تانيه
    0.43
    nelson
    0.41
    CloseOperation
    0.41
     Hurt
    0.41
    Activations Density 0.638%

    No Known Activations