© 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. 22-GEMMASCOPE-RES-16K
    11. 11332
    Prev
    Next
    INDEX
    Explanations

    quantitative references or estimates related to research findings

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

    Followed by nouns indicating quantity

    np_acts-logits-general · gemini-2.0-flash

    many, several, some, certain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    both
    -0.60
    X
    -0.52
    J
    -0.52
    E
    -0.51
    /
    -0.51
    H
    -0.50
    the
    -0.50
    Most
    -0.49
     thingy
    -0.49
    Z
    -0.49
    POSITIVE LOGITS
    '],
    0.89
    "],
    0.87
    NUMX
    0.87
    >--}}
    0.87
     notable
    0.86
    ]();
    0.86
    .}(
    0.83
    "]);
    0.83
    ]:
    0.83
     kinds
    0.82
    Activations Density 0.780%

    No Known Activations