© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12607
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions that involve data structure properties and nodes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )":
    -0.55
     ";
    
    -0.55
    .";
    
    -0.54
    >`;
    -0.54
    ]]:
    -0.53
    ications
    -0.53
    >";
    
    -0.53
     ';
    
    -0.51
    "]));
    -0.51
    AppMethodBeat
    -0.51
    POSITIVE LOGITS
     estekak
    0.90
    脚注の使い方
    0.58
    adaptiveStyles
    0.56
    مصادر
    0.53
     cherchés
    0.53
    Rujuakan
    0.52
     Cup
    0.51
     Khr
    0.50
    bracelet
    0.49
    новништво
    0.49
    Activations Density 0.367%

    No Known Activations