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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 58041
    Prev
    Next
    INDEX
    Explanations

    phrases and subjects related to people and their experiences or roles

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

    there are

    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
    extra
    -0.36
    trans
    -0.32
    เท
    -0.32
    survi
    -0.32
    sur
    -0.32
    sc
    -0.32
    grey
    -0.32
     TRANS
    -0.32
    choice
    -0.31
     Böh
    -0.31
    POSITIVE LOGITS
    ThroughAttribute
    0.73
     للاسماء
    0.71
     esternos
    0.61
    المناصب
    0.60
    saraba
    0.59
    SBATCH
    0.59
    errHandler
    0.57
    AndroidJUnit
    0.57
    IsContent
    0.57
    tanleria
    0.55
    Activations Density 0.051%

    No Known Activations