© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4405
    Prev
    Next
    INDEX
    Explanations

    commands and methods related to data processing and iteration in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.25
     NSCoder
    -1.08
     lenker
    -0.99
    principalColumn
    -0.99
     onPostExecute
    -0.98
     EconPapers
    -0.98
    Vidite
    -0.97
    Personendaten
    -0.94
    HasAnnotation
    -0.93
    XmlAccessorType
    -0.93
    POSITIVE LOGITS
    Output
    1.00
     output
    0.94
    output
    0.85
     Output
    0.82
    enumi
    0.80
    nextInt
    0.73
    OUTPUT
    0.71
     OUTPUT
    0.61
    输出
    0.61
     outputs
    0.56
    Activations Density 0.008%

    No Known Activations