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. 4-GEMMASCOPE-RES-16K
    6. 10901
    Prev
    Next
    INDEX
    Explanations

    numerical representations or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.95
     يتيمه
    -0.82
    клопе
    -0.81
     utafitiHapana
    -0.80
     ERSITY
    -0.75
     RSITY
    -0.74
    ItemBackground
    -0.74
    Читати
    -0.73
     Voy
    -0.72
    rawDesc
    -0.72
    POSITIVE LOGITS
    ,
    0.77
    </td>
    0.60
    ";
    0.58
    ';
    0.56
    },
    0.55
    };
    0.54
     };
    0.54
     ,
    0.54
    </th>
    0.53
    ")));
    0.53
    Activations Density 0.215%

    No Known Activations