© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 10332
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related structures in programming or data handling

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

    detail or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.55
    principalColumn
    -0.44
    OGND
    -0.38
    AddTagHelper
    -0.38
     abandonné
    -0.35
    penup
    -0.35
    IsMutable
    -0.35
     omge
    -0.35
    homonymie
    -0.34
     OnEnable
    -0.34
    POSITIVE LOGITS
     detail
    1.09
    detail
    1.00
     detailed
    0.99
     details
    0.97
     Detail
    0.93
     DETAIL
    0.92
    Detail
    0.90
     detal
    0.88
    DETAIL
    0.86
    detailed
    0.84
    Activations Density 0.010%

    No Known Activations