© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5334
    Prev
    Next
    INDEX
    Explanations

    phrases related to failures, risks, and the importance of prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.63
     Administrativna
    -0.62
     }{@
    -0.59
     beginnetje
    -0.59
    Pautan
    -0.57
    }());
    -0.57
    λέον
    -0.56
    ArgsConstructor
    -0.56
    tvguidetime
    -0.56
    новништво
    -0.56
    POSITIVE LOGITS
    arga
    0.56
    せっかく
    0.54
     contract
    0.49
     future
    0.49
     malah
    0.48
    DCM
    0.48
    future
    0.47
    thard
    0.47
    bahn
    0.46
     nantinya
    0.46
    Activations Density 0.423%

    No Known Activations