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. 8552
    Prev
    Next
    INDEX
    Explanations

    scientific terms and comparisons related to biochemical substances and processes

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

    Tokens before or after "vs"

    np_acts-logits-general · gemini-2.0-flash

    vs / greater than or control

    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
     }}$}
    -1.27
    )");
    
    -1.23
     ]
    
    -1.19
     "];
    -1.18
    ."));
    -1.17
    };*/
    -1.16
    }")
    
    -1.16
    '):
    
    -1.15
    %");
    -1.13
    .";
    
    -1.12
    POSITIVE LOGITS
     vs
    0.97
     +
    0.86
     /
    0.76
     versus
    0.74
    +
    0.68
    vs
    0.67
     ->
    0.66
     Vs
    0.65
     VS
    0.63
    /
    0.63
    Activations Density 0.884%

    No Known Activations