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. 6159
    Prev
    Next
    INDEX
    Explanations

    attends to various forms of the token "move" from related tokens that signal progression or transition

    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
    0:0.06
    1:0.03
    2:0.05
    3:0.05
    4:0.59
    5:0.06
    6:0.05
    7:0.08
    Negative Logits
     väli
    -0.38
     Bact
    -0.36
     Chwiliwch
    -0.36
     Haram
    -0.35
    krishnan
    -0.35
    Scope
    -0.35
     ſtate
    -0.34
     Cæsar
    -0.34
     ſch
    -0.34
     labi
    -0.33
    POSITIVE LOGITS
    XmlEnum
    0.41
     typelib
    0.40
     المعيارى
    0.39
    CGContext
    0.37
    ANTLR
    0.35
     TextInputType
    0.35
     pangan
    0.34
     Audiodateien
    0.34
    labelledby
    0.33
     '';
    
    0.33
    Activations Density 0.087%

    No Known Activations