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. 19-GEMMASCOPE-RES-16K
    6. 265
    Prev
    Next
    INDEX
    Explanations

    legal claims and references to legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.56
    ]-->
    -0.56
    abestanden
    -0.55
    usercontent
    -0.55
    Sent
    -0.47
     Sent
    -0.46
     '\\;'
    -0.45
    </tfoot>
    -0.45
    참고
    -0.45
     مشين
    -0.44
    POSITIVE LOGITS
     lawsuit
    1.62
     lawsuits
    1.45
     sued
    1.35
     suing
    1.35
     suit
    1.30
     complaint
    1.27
     litigation
    1.22
     claim
    1.20
     sue
    1.17
     claims
    1.13
    Activations Density 1.293%

    No Known Activations