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. 0-GEMMASCOPE-RES-16K
    6. 9327
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement or actions involving stepping or stepping down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idea
    -0.56
     R
    -0.52
     Obrador
    -0.51
     reda
    -0.50
    Calais
    -0.48
    sweise
    -0.48
     Idea
    -0.47
    uertos
    -0.46
    UGAL
    -0.45
    iciens
    -0.45
    POSITIVE LOGITS
     stepping
    0.89
     stepped
    0.88
     Efq
    0.86
     Shakspeare
    0.83
     myſelf
    0.78
     Houſe
    0.77
     Diſ
    0.74
     stiefel
    0.74
     Monfieur
    0.73
    ons
    0.73
    Activations Density 0.120%

    No Known Activations