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. 6031
    Prev
    Next
    INDEX
    Explanations

    attends to the words "bit" and "a" from various contexts, often followed by descriptive tokens

    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
    0:0.22
    1:0.20
    2:0.21
    3:0.04
    4:0.04
    5:0.02
    6:0.04
    7:0.20
    Negative Logits
     typelib
    -0.26
    oredCriteria
    -0.24
     Tew
    -0.24
    psack
    -0.23
    ddar
    -0.22
     समीक्षक
    -0.22
    ardians
    -0.22
    thoscope
    -0.22
    YNC
    -0.22
    edipus
    -0.21
    POSITIVE LOGITS
    +#+#
    0.35
    ArgsConstructor
    0.34
    complexType
    0.34
    addContainerGap
    0.33
    存于互联网档案馆
    0.30
     ويكيميديا
    0.29
     فريبيس
    0.28
    μβρίου
    0.28
     nargin
    0.28
     combineReducers
    0.28
    Activations Density 0.213%

    No Known Activations