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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 32006
    Prev
    Next
    INDEX
    Explanations

    references to the word "back" in various contexts

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

    back at home or then

    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
     suivantes
    -0.44
    ,
    -0.41
     Romains
    -0.40
     России
    -0.39
    tudiant
    -0.39
    Geplaatst
    -0.38
    parsedMessage
    -0.38
     rağmen
    -0.37
     and
    -0.37
     alis
    -0.37
    POSITIVE LOGITS
    PreferredItem
    0.72
    GEBURTS
    0.70
    arangay
    0.68
    alakip
    0.66
    Ārējās
    0.61
    Pautan
    0.59
     hObject
    0.58
    ⤒
    0.57
    mpagne
    0.57
    ésult
    0.56
    Activations Density 0.052%

    No Known Activations