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. 23878
    Prev
    Next
    INDEX
    Explanations

    terms related to preservation and change in various contexts

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

    verbs followed by clauses or descriptions

    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
    رشف
    -0.53
     ciudadana
    -0.53
    rungsseite
    -0.51
     poveznice
    -0.51
     EconPapers
    -0.49
     avulla
    -0.49
     maș
    -0.48
    AutoScaleMode
    -0.48
     ulei
    -0.47
    
    -0.47
    POSITIVE LOGITS
     squee
    0.45
     Works
    0.42
    TypedDataSet
    0.41
    '">
    0.41
    '));
    
    0.40
     Was
    0.40
     Rea
    0.39
    ']);
    
    0.39
    '):
    
    0.39
     mongoose
    0.38
    Activations Density 0.274%

    No Known Activations