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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14971
    Prev
    Next
    INDEX
    Explanations

    web-related links and resources

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

    Links to files and web pages

    np_acts-logits-general · gemini-2.0-flash

    URLs and links to documents

    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
     […]
    -1.43
    </blockquote>
    -1.21
    </i>
    -1.18
    <eos>
    -1.17
    […]
    -1.09
    </em>
    -1.09
    </h6>
    -0.97
     [...]
    -0.94
    ↵↵
    -0.89
    <strong>
    -0.87
    POSITIVE LOGITS
    }{
    2.30
    /}{
    1.79
     }{
    1.31
    )}{
    1.25
    }{\
    1.20
    }{(
    1.05
    }{-
    1.04
    }{|
    1.00
    :}
    1.00
    }}{
    0.99
    Activations Density 0.008%

    No Known Activations