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. 6102
    Prev
    Next
    INDEX
    Explanations

    attends to descriptions of various fields from corresponding closing descriptions of fields

    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
    0:0.03
    1:0.65
    2:0.05
    3:0.02
    4:0.05
    5:0.07
    6:0.04
    7:0.05
    Negative Logits
    ThroughAttribute
    -0.37
     description
    -0.35
    AddTagHelper
    -0.34
    omeness
    -0.32
    matchCondition
    -0.32
    dorfer
    -0.31
     Description
    -0.30
    mediately
    -0.29
    ineſs
    -0.29
    — 
    -0.29
    POSITIVE LOGITS
     eût
    0.32
     pettico
    0.28
     uncin
    0.28
     AssemblyCulture
    0.27
     Whig
    0.27
     saç
    0.26
    الحياه
    0.25
     Scip
    0.25
     élevés
    0.24
    GetAxis
    0.24
    Activations Density 0.039%

    No Known Activations