© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5911
    Prev
    Next
    INDEX
    Explanations

    references to funding sources and financial support in research contexts

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

    European institutions or funding

    np_acts-logits-general · gemini-2.0-flash

    European institutions and grants

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tahankan
    -0.41
     ?',
    -0.38
     мимо
    -0.37
    mstyle
    -0.37
    Gön
    -0.36
    OuterClass
    -0.36
    ...\
    -0.35
    izability
    -0.35
    naio
    -0.35
     utility
    -0.35
    POSITIVE LOGITS
     Europeo
    0.52
     autorytatywna
    0.51
     europeo
    0.51
     européen
    0.50
    RTDA
    0.48
     Europy
    0.44
    ChildScrollView
    0.44
     EUROPEAN
    0.43
     européens
    0.43
    Див
    0.42
    Activations Density 0.380%

    No Known Activations