© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57563
    Prev
    Next
    INDEX
    Explanations

    cryptographic algorithms and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elfde
    -0.57
    llary
    -0.48
    PrototypeOf
    -0.46
    modo
    -0.45
     kuulu
    -0.45
     néz
    -0.45
    fej
    -0.44
    ági
    -0.44
     capito
    -0.44
     Bande
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.87
    MemoryWarning
    0.84
    ConstraintMaker
    0.82
     myſelf
    0.79
     fevere
    0.77
     himſelf
    0.76
     Shakspeare
    0.73
     CreateTagHelper
    0.73
    MLLoader
    0.72
    IntoConstraints
    0.72
    Activations Density 0.188%

    No Known Activations