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. 6279
    Prev
    Next
    INDEX
    Explanations

    attends to the placement of specific characters or formatting from later sections of the string

    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
    0:0.08
    1:0.10
    2:0.10
    3:0.10
    4:0.10
    5:0.08
    6:0.20
    7:0.20
    Negative Logits
    KURZBESCHREIBUNG
    -0.39
    readystatechange
    -0.34
    Tē
    -0.32
    tagHelperRunner
    -0.31
    rzez
    -0.31
    __*/
    -0.30
     ***!
    -0.29
     समीक्षक
    -0.29
     IDisposable
    -0.29
     ExecuteAsync
    -0.29
    POSITIVE LOGITS
    <h6>
    0.32
    Viel
    0.29
    umatic
    0.28
    LElement
    0.27
    StateList
    0.26
     Roskov
    0.26
     cod
    0.25
    ьаж
    0.25
    Continue
    0.25
    namentales
    0.25
    Activations Density 0.060%

    No Known Activations