© 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. 3-GEMMASCOPE-RES-16K
    6. 11783
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "af" in various contexts or formats, likely indicating an interest in specific codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.97
    省市镇
    -0.85
     Meksiku
    -0.82
    
    -0.73
    coj
    -0.72
     chay
    -0.70
    angler
    -0.70
    SourceChecksum
    -0.69
     Silla
    -0.68
     assi
    -0.67
    POSITIVE LOGITS
    af
    2.69
    AF
    2.53
     AF
    2.48
     af
    2.39
     Af
    2.25
    Af
    2.08
     AFF
    1.14
    AFN
    1.11
    afs
    1.08
     afl
    1.03
    Activations Density 0.131%

    No Known Activations