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. 13521
    Prev
    Next
    INDEX
    Explanations

    class and component definitions in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    );
    -0.60
    .
    -0.60
    ),
    -0.60
    ?).
    -0.60
    .)
    -0.59
    ).
    -0.58
    ].
    -0.57
    ?),
    -0.55
    .");
    -0.55
    *);
    -0.55
    POSITIVE LOGITS
     extends
    1.40
    IntoConstraints
    0.90
    setVerticalGroup
    0.90
     Drapeau
    0.85
     дописавши
    0.84
     للاسماء
    0.82
    __":
    
    0.82
    RegressionTest
    0.80
    __':
    
    0.80
     Normdatei
    0.80
    Activations Density 0.085%

    No Known Activations