© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4869
    Prev
    Next
    INDEX
    Explanations

    terms related to authority, governance, and administrative roles

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

    German noun suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.64
    LayoutStyle
    -0.63
    SequentialGroup
    -0.63
     noqa
    -0.62
    csname
    -0.59
     onResume
    -0.59
     esternos
    -0.58
    RTLR
    -0.58
    ServletException
    -0.57
     لينك
    -0.57
    POSITIVE LOGITS
    nungs
    0.62
    itäts
    0.53
    rijfs
    0.50
     arbejds
    0.50
    chafts
    0.50
    ierungs
    0.49
    gnings
    0.48
    ikations
    0.48
    tschafts
    0.48
    tungs
    0.46
    Activations Density 0.028%

    No Known Activations