Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 6115
    Prev
    Next
    INDEX
    Explanations

    attends to method call tokens marked with parentheses from function return type tokens earlier in the sequence

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.10
    2:0.07
    3:0.04
    4:0.08
    5:0.05
    6:0.08
    7:0.45
    Negative Logits
    хьтан
    -0.44
     ContentValues
    -0.41
     transfieras
    -0.40
    SharedDtor
    -0.39
    UnusedPrivate
    -0.39
    propTypes
    -0.39
     myſelf
    -0.39
     themſelves
    -0.38
     unſ
    -0.37
     BoxFit
    -0.37
    POSITIVE LOGITS
    utan
    0.30
    —-
    0.30
    PointerException
    0.28
    ——-
    0.28
    —
    0.28
    pop
    0.28
     Pop
    0.27
    休
    0.27
    —————
    0.27
    alu
    0.27
    Activations Density 0.013%

    No Known Activations