Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5233
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

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

    LaTeX math symbols and ampersands

    np_acts-logits-general · gemini-2.0-flash

    & symbol and other markup

    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
    <b>
    -0.77
    <strong>
    -0.69
    '}>
    -0.53
    ?”.
    -0.53
    )。
    -0.51
    »).
    -0.51
    ).\\
    -0.51
    ".$_
    -0.51
    ?".
    -0.50
    "}>
    -0.50
    POSITIVE LOGITS
     &
    1.49
    </strong>
    1.00
    </td>
    1.00
     للاسماء
    0.99
     متعلقه
    0.93
     &,
    0.92
    }&
    0.91
    </code>
    0.90
    )&
    0.89
    ,&
    0.89
    Activations Density 0.287%

    No Known Activations