© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5526
    Prev
    Next
    INDEX
    Explanations

    common elements in formal correspondence

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

    Tokens after specific punctuation ([, :, *, or \'])

    np_acts-logits-general · gemini-2.0-flash

    sequence of X's

    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
    )");
    -1.21
     }}$}
    -1.18
    )";
    -1.08
    ")));
    -1.06
    ]--;
    -1.05
    !")
    -1.02
    ]));
    -1.02
    '},
    -1.02
    .")]
    -1.00
    ."));
    -1.00
    POSITIVE LOGITS
     X
    1.51
    xxx
    1.41
    XXX
    1.36
     XYZ
    1.35
    X
    1.35
    XX
    1.35
     XXX
    1.35
     x
    1.28
     xxx
    1.27
    〇〇
    1.25
    Activations Density 1.260%

    No Known Activations