© 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. 17913
    Prev
    Next
    INDEX
    Explanations

    terms related to liver diseases and conditions, particularly hepatocellular carcinoma

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

    hepatotoxicity, hepatocellular, hepatocyte

    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
     picket
    -0.47
     كومونز
    -0.45
    ::_('
    -0.45
    uxxxx
    -0.45
     kaarangay
    -0.44
     Zin
    -0.44
     tel
    -0.44
    divarius
    -0.43
     Tuff
    -0.43
    Bom
    -0.43
    POSITIVE LOGITS
     hígado
    1.15
     hepat
    1.08
     liver
    1.06
     hepatic
    1.02
     Liver
    0.96
     livers
    0.94
    Liver
    0.90
    肝
    0.86
     LIVER
    0.81
     печени
    0.79
    Activations Density 0.048%

    No Known Activations