© 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. 15-GEMMASCOPE-RES-16K
    11. 2523
    Prev
    Next
    INDEX
    Explanations

    HTML formatting elements like italics and emphasis tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Географиясе
    -0.86
    rinfo
    -0.85
    arakhand
    -0.82
     ddelweddau
    -0.81
    ombic
    -0.77
    AsUp
    -0.77
    Према
    -0.74
    🔟
    -0.73
    neux
    -0.73
    Glej
    -0.72
    POSITIVE LOGITS
    <em>
    2.01
    </em>
    1.78
    <i>
    1.44
    <strong>
    1.38
    <u>
    1.32
    <code>
    1.18
    <sub>
    0.94
    <h3>
    0.89
    </i>
    0.89
    <s>
    0.86
    Activations Density 0.004%

    No Known Activations