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. 5911
    Prev
    Next
    INDEX
    Explanations

    attends to instances of "IOException" from tokens that signal continuations or terminations in code statements

    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
    0:0.13
    1:0.25
    2:0.20
    3:0.05
    4:0.15
    5:0.04
    6:0.07
    7:0.07
    Negative Logits
     AssemblyTitle
    -0.40
    ]='\
    -0.38
    --]
    -0.36
    oleum
    -0.35
    cendental
    -0.34
    SequentialGroup
    -0.33
    ductory
    -0.33
     onCancelled
    -0.33
     )))
    -0.31
    </>
    -0.31
    POSITIVE LOGITS
    Xna
    0.50
    expandindo
    0.43
    LookAnd
    0.39
    ntax
    0.34
    ậc
    0.33
    HtmlAttribute
    0.32
    Obrázky
    0.31
     MessageBoxIcon
    0.31
    indicator
    0.31
     prochains
    0.31
    Activations Density 0.010%

    No Known Activations