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. 0-GEMMASCOPE-ATT-16K
    6. 6187
    Prev
    Next
    INDEX
    Explanations

    attends to the concept of "mind" from related mental constructs or terminologies represented later in the sequence

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.05
    1:0.20
    2:0.12
    3:0.03
    4:0.24
    5:0.18
    6:0.05
    7:0.09
    Negative Logits
    ,
    -0.39
    ↵
    -0.38
     of
    -0.36
    -
    -0.31
    ing
    -0.31
     but
    -0.31
    age
    -0.30
    a
    -0.30
     (
    -0.30
     and
    -0.30
    POSITIVE LOGITS
    bootstrapcdn
    0.59
    endphp
    0.50
    posedge
    0.50
    __':
    
    0.48
    jooq
    0.48
    aarrggbb
    0.47
    fastjson
    0.45
    /−
    0.45
    SDAY
    0.44
     للاسماء
    0.44
    Activations Density 0.039%

    No Known Activations