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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12074
    Prev
    Next
    INDEX
    Explanations

    references to links or hyperlinks within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.51
    ))))))))
    -0.49
    __":
    
    -0.48
    ")))
    -0.48
    })).
    -0.46
    ."));
    -0.46
    )])
    -0.45
    )")
    -0.45
    ')));
    -0.44
    .");
    -0.44
    POSITIVE LOGITS
     link
    1.35
     Link
    1.33
    link
    1.31
    Link
    1.29
     LINK
    1.23
     links
    1.20
    links
    1.19
     LINKS
    1.19
    LINK
    1.19
     Links
    1.18
    Activations Density 0.105%

    No Known Activations