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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14406
    Prev
    Next
    INDEX
    Explanations

    key programming syntax and structure in code snippets

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

    PHP code or code snippets

    np_acts-logits-general · gemini-2.0-flash

    PHP and SQL code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )’
    -0.57
     }}$}
    -0.56
    '));
    
    -0.55
    ).
    
    -0.54
    '},
    
    -0.54
    ")]
    
    -0.53
    ).'
    -0.51
    .”)
    -0.50
    )​
    -0.49
    "]);
    
    -0.48
    POSITIVE LOGITS
    <?
    1.03
    #{
    1.00
     #{
    0.99
     <?
    0.96
     Roskov
    0.95
    {{
    0.94
    ${
    0.94
     <?=
    0.93
    <?=
    0.91
    ItemBackground
    0.90
    Activations Density 0.564%

    No Known Activations