© 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. 15750
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "head" and its various contexts

    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
    Allo
    -0.72
     nahilalakip
    -0.72
     disponibilités
    -0.71
    UNITY
    -0.68
    ="{{$
    -0.66
     Chisholm
    -0.64
    miracle
    -0.64
     Thurman
    -0.63
     Lester
    -0.63
    ⓘ
    -0.63
    POSITIVE LOGITS
     head
    2.69
     Head
    2.57
     HEAD
    2.55
    Head
    2.47
     heads
    2.41
    head
    2.31
    HEAD
    2.23
     Heads
    2.15
    heads
    2.03
    Heads
    1.92
    Activations Density 0.037%

    No Known Activations