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. 6288
    Prev
    Next
    INDEX
    Explanations

    attends to department-related tokens from institution-related 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
    0:0.16
    1:0.23
    2:0.16
    3:0.07
    4:0.06
    5:0.02
    6:0.08
    7:0.18
    Negative Logits
    ?";
    -0.30
     --;
    -0.27
    IFER
    -0.25
    )?
    -0.24
     Historical
    -0.24
     */;
    -0.24
    }>;
    -0.23
     feature
    -0.23
    hasOwnProperty
    -0.23
    _();
    -0.23
    POSITIVE LOGITS
    sizeCache
    0.51
     doInBackground
    0.45
     متعلقه
    0.41
    脚注の使い方
    0.41
    AutoScaleMode
    0.37
    GetBytes
    0.37
    InjectAttribute
    0.36
    Geplaatst
    0.36
    ftagPool
    0.36
     المعيارى
    0.36
    Activations Density 0.655%

    No Known Activations