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. 10-GEMMASCOPE-RES-16K
    6. 13317
    Prev
    Next
    INDEX
    Explanations

    elements and phrases related to sound and audio, particularly in a dramatic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -1.28
     AssemblyCulture
    -0.89
     Roskov
    -0.81
     referenties
    -0.79
     للاسماء
    -0.79
    principalTable
    -0.77
    MessageOf
    -0.74
    saraba
    -0.71
    featureID
    -0.71
    Tazama
    -0.70
    POSITIVE LOGITS
     Apare
    0.46
    makeText
    0.45
    ruptedException
    0.42
    UserScript
    0.42
     Suddenly
    0.42
     boo
    0.42
    atel
    0.41
    Suddenly
    0.41
    /@
    0.41
     bla
    0.41
    Activations Density 0.239%

    No Known Activations