© 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. 97352
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating reasons or justifications

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

    each other / mutual relationships

    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
    SourceChecksum
    -0.38
    Cuc
    -0.33
    "]);
    -0.32
    "");
    -0.30
    "));
    
    -0.29
    )</
    -0.29
     alpes
    -0.29
     injust
    -0.29
    "",
    
    -0.29
     illiterate
    -0.29
    POSITIVE LOGITS
     nhau
    3.25
    กัน
    1.04
     varandra
    0.98
     elkaar
    0.96
     กัน
    0.88
    ArgsConstructor
    0.87
    ModelAdmin
    0.78
    tagHelperRunner
    0.77
     eachother
    0.77
     einander
    0.76
    Activations Density 0.001%

    No Known Activations