© 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. 4-GEMMASCOPE-RES-16K
    11. 15758
    Prev
    Next
    INDEX
    Explanations

    terms and flags related to compiler settings and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.76
    CSRF
    -0.68
     noDo
    -0.66
     pinulongan
    -0.64
    ftagPool
    -0.62
    ValueStyle
    -0.62
    ViewFeatures
    -0.61
     createSlice
    -0.61
    LookAnd
    -0.61
    EndContext
    -0.60
    POSITIVE LOGITS
    toupper
    0.56
    Sklici
    0.49
     "',
    0.49
    bigoplus
    0.49
     ulang
    0.47
    rops
    0.47
    [[
    0.46
    EMOS
    0.46
     mídia
    0.46
     tinggi
    0.45
    Activations Density 0.226%

    No Known Activations