Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6651
    Prev
    Next
    INDEX
    Explanations

    attends to action-oriented tokens from subsequent response-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
    0:0.09
    1:0.10
    2:0.09
    3:0.14
    4:0.12
    5:0.07
    6:0.19
    7:0.17
    Negative Logits
     Roskov
    -0.36
    ()]
    
    -0.34
    UnsafeEnabled
    -0.34
    SuppressMessage
    -0.27
    !")
    
    -0.27
    ()]);
    -0.27
     ""}
    -0.27
    itri
    -0.27
     comfor
    -0.26
    InjectAttribute
    -0.26
    POSITIVE LOGITS
    Tikang
    0.30
    Vidite
    0.29
    partimento
    0.28
    licherweise
    0.27
    icestershire
    0.26
    ésult
    0.26
    HomeAsUpEnabled
    0.25
    davis
    0.25
    يكب
    0.25
    tonode
    0.24
    Activations Density 1.449%

    No Known Activations