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. 20-GEMMASCOPE-RES-16K
    6. 10966
    Prev
    Next
    INDEX
    Explanations

    temporal references and context of events, particularly related to incidents or actions

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

    Japanese sentence fragments before sentence endings

    np_acts-logits-general · gemini-2.0-flash

    speech/state concluding particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.71
    )");
    
    -0.71
    kháu
    -0.70
    Билгалдахарш
    -0.69
    })*/
    -0.68
    клопе
    -0.67
    ?')
    -0.65
    });*/
    -0.63
    WriteAttribute
    -0.61
    ]--;
    -0.60
    POSITIVE LOGITS
    。
    0.75
    이다
    0.71
    ।
    0.63
     rather
    0.63
    adır
    0.61
     whereas
    0.60
    EditorBrowsable
    0.59
    임
    0.57
    DebuggerNonUser
    0.56
    rather
    0.56
    Activations Density 0.064%

    No Known Activations