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. 23-GEMMASCOPE-RES-16K
    6. 6246
    Prev
    Next
    INDEX
    Explanations

    code-related terms and expressions, particularly those related to string manipulation and document handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -0.65
    发表于
    -0.61
     hasattr
    -0.61
    <>());
    -0.56
    {})
    -0.54
     {},
    
    -0.51
    InstanceOf
    -0.51
    ({});
    -0.50
    )=>{
    
    -0.49
    colección
    -0.48
    POSITIVE LOGITS
    DoubleQuotes
    0.71
     InputDecoration
    0.71
    AndEndTag
    0.70
     substring
    0.68
    +"
    0.67
     StringTokenizer
    0.65
    IBarButtonItem
    0.63
    +'
    0.63
    extAlignment
    0.62
    +",
    0.61
    Activations Density 0.119%

    No Known Activations