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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29767
    Prev
    Next
    INDEX
    Explanations

    code elements related to data handling in programming

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

    POST requests and code snippets

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ProtoMessage
    -0.44
    äts
    -0.42
    #
    -0.39
    qJ
    -0.39
    fromLTRB
    -0.38
     poz
    -0.38
    대
    -0.38
     PeEnEo
    -0.38
    OGEN
    -0.38
    heta
    -0.38
    POSITIVE LOGITS
    LabelTagHelper
    0.57
    WithIOException
    0.52
     ब्रेकडाउन
    0.49
    aarrggbb
    0.48
    AntiForgeryToken
    0.45
    niająca
    0.45
    transQ
    0.45
    postIndex
    0.44
     Allociné
    0.41
    Portale
    0.41
    Activations Density 0.005%

    No Known Activations