© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13775
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to quantum mechanics and linear algebra

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

    Mathematical notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]$
    -1.71
    .$
    -1.65
    }$
    -1.65
    |$
    -1.62
    ))$
    -1.60
    $
    -1.59
    ).$
    -1.58
    ;$
    -1.55
     )$
    -1.54
    )$,
    -1.54
    POSITIVE LOGITS
    </h6>
    0.66
    </h2>
    0.63
    </h3>
    0.59
     GenerationType
    0.52
    DoubleQuotes
    0.49
    MessageTagHelper
    0.49
    </h5>
    0.49
     дописавши
    0.49
    AnchorStyles
    0.48
    IsMutable
    0.47
    Activations Density 3.166%

    No Known Activations