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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 45782
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions related to eligibility for clinical trials

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

    diagnosis or history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.37
    %");
    -0.30
    ''');
    -0.29
    üstet
    -0.28
     }}"></
    -0.28
    %"),
    -0.28
    }),
    
    -0.28
    UPDATED
    -0.27
    "]);
    -0.27
     improved
    -0.26
    POSITIVE LOGITS
    StructEnd
    0.57
     ब्रेकडाउन
    0.57
     ujednoznacz
    0.56
     betweenstory
    0.54
    any
    0.52
     BrowserModule
    0.52
    GEBURTS
    0.52
    anything
    0.52
    ConstraintMaker
    0.51
     quaisquer
    0.51
    Activations Density 0.033%

    No Known Activations