© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12608
    Prev
    Next
    INDEX
    Explanations

    references to selection or choice within text

    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
    CFLAGS
    -0.74
     kém
    -0.74
    Enlaces
    -0.73
    ThemeOverlay
    -0.72
     Audiodateien
    -0.72
    toCharArray
    -0.72
    úly
    -0.71
    ]='\
    -0.71
    imakasih
    -0.71
     թվական
    -0.69
    POSITIVE LOGITS
    Select
    2.04
     Select
    2.02
    select
    1.97
     SELECT
    1.93
     select
    1.88
    SELECT
    1.76
     selects
    1.62
    Sele
    1.45
     selectAll
    1.43
     Sele
    1.35
    Activations Density 0.059%

    No Known Activations