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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 7867
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases

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

    Comes before alternatives or options

    np_acts-logits-general · gemini-2.0-flash

    alternative recommendations and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )');
    -0.65
    ?";
    -0.62
    佗
    -0.61
    ')";
    -0.58
    ]));
    
    -0.57
    "");
    -0.57
    ]<<"
    -0.57
    eaways
    -0.56
    ?");
    -0.56
    /');
    -0.55
    POSITIVE LOGITS
     beware
    1.09
     you
    1.03
     Beware
    0.95
    おすすめです
    0.95
    Beware
    0.93
    you
    0.90
     You
    0.89
    Alternatively
    0.87
     Alternatively
    0.87
    オススメです
    0.86
    Activations Density 0.217%

    No Known Activations