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. 8-GEMMASCOPE-RES-16K
    6. 8763
    Prev
    Next
    INDEX
    Explanations

    file types or extensions related to compressed data

    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
     CreateTagHelper
    -1.17
    enumi
    -1.13
    expandindo
    -0.95
    enumii
    -0.89
    GeneratedValue
    -0.88
    BeginContext
    -0.88
     MainAxisSize
    -0.83
     ExecuteAsync
    -0.81
    ViewFeatures
    -0.80
    INCREF
    -0.80
    POSITIVE LOGITS
    AccessorTable
    0.71
    DISPLAY
    0.53
    colgroup
    0.48
     <!--
    0.46
    context
    0.45
     scuole
    0.45
     Fant
    0.45
    новништво
    0.45
    doc
    0.44
     برانيه
    0.44
    Activations Density 0.002%

    No Known Activations