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. 6170
    Prev
    Next
    INDEX
    Explanations

    attends to the concentration measure "mM" from the related ions or compounds in the context of biochemical processes

    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
    0:0.01
    1:0.05
    2:0.10
    3:0.19
    4:0.10
    5:0.11
    6:0.23
    7:0.17
    Negative Logits
    ↵↵
    -0.56
     EconPapers
    -0.49
     invokingState
    -0.48
     становника
    -0.47
    hynch
    -0.43
    indd
    -0.41
    UserScript
    -0.40
    twimg
    -0.39
     and
    -0.39
    ientôt
    -0.39
    POSITIVE LOGITS
     dafs
    0.46
    bir
    0.46
     pegat
    0.43
    entown
    0.43
     PTS
    0.43
     fevere
    0.43
     auffi
    0.43
     Patro
    0.43
    altra
    0.42
     mapStateToProps
    0.42
    Activations Density 1.568%

    No Known Activations