© 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. 5-GEMMASCOPE-RES-16K
    11. 4940
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "head" and its various forms and combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.90
    Allo
    -0.71
     disponibilités
    -0.70
    UNITY
    -0.69
    rungsseite
    -0.65
    ⓘ
    -0.65
    --}}
    -0.64
    miracle
    -0.64
    COLORS
    -0.64
     Lester
    -0.63
    POSITIVE LOGITS
     head
    2.56
     HEAD
    2.48
     Head
    2.46
    Head
    2.37
     heads
    2.36
    head
    2.25
    HEAD
    2.15
     Heads
    2.12
    heads
    1.98
    Heads
    1.89
    Activations Density 0.042%

    No Known Activations