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. 6189
    Prev
    Next
    INDEX
    Explanations

    attends to phrases indicating location or context from phrases providing detailed descriptions of subsequent items

    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
    0:0.06
    1:0.13
    2:0.06
    3:0.06
    4:0.11
    5:0.44
    6:0.06
    7:0.05
    Negative Logits
    Apparently
    -0.22
    timeScale
    -0.20
    ध्यम
    -0.19
    mml
    -0.19
     Apparently
    -0.19
    zenberg
    -0.19
     jurisdic
    -0.19
     censiti
    -0.19
     Webseite
    -0.19
    laston
    -0.19
    POSITIVE LOGITS
     виправивши
    0.36
    DebuggerStep
    0.35
    setVerticalGroup
    0.33
    RenderAtEndOf
    0.32
    gehenden
    0.31
    endphp
    0.30
    abstractmethod
    0.28
    ''')
    0.28
    (",");
    0.27
    Бахар
    0.27
    Activations Density 0.115%

    No Known Activations