© 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. 64906
    Prev
    Next
    INDEX
    Explanations

    terms related to completion or status indicators

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

    uncompleted, not yet, unwatched

    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
    SPJ
    -0.54
    agues
    -0.51
    ANTAGE
    -0.49
    ckså
    -0.49
    inflater
    -0.48
    DbType
    -0.48
     razón
    -0.47
    darah
    -0.47
    PullParser
    -0.46
     Teléfono
    -0.46
    POSITIVE LOGITS
    未
    1.96
     未
    1.50
    还未
    1.06
     chưa
    1.02
    尚未
    0.98
     Belum
    0.91
     belum
    0.90
    并未
    0.89
    未能
    0.85
    从未
    0.79
    Activations Density 0.002%

    No Known Activations