Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12572
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific and legal contexts

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

    Followed by a comma or parenthesis

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %");
    -0.96
    ."));
    -0.93
    '}>
    -0.90
    %";
    -0.89
    "];
    
    -0.87
    GraphicsUnit
    -0.86
    */;
    -0.86
    "]}
    -0.85
    ")));
    
    -0.85
    ]$}
    -0.84
    POSITIVE LOGITS
    )
    1.05
    ),
    0.68
     appunto
    0.62
     estekak
    0.61
     )
    0.58
     gena
    0.54
    ]
    0.54
    )
    0.48
     genannt
    0.46
     genoemd
    0.46
    Activations Density 1.151%

    No Known Activations