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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1192
    Prev
    Next
    INDEX
    Explanations

    attends from the front insertion of glucans and sugars to the numerically-matched descriptive closing characters

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    1:0.03
    2:0.01
    3:0.01
    4:0.01
    5:0.02
    6:0.45
    7:0.22
    8:0.02
    9:0.01
    10:0.02
    11:0.01
    12:0.01
    13:0.01
    14:0.04
    15:0.03
    Negative Logits
    	
    -0.21
     bēr
    -0.19
     juos
    -0.19
     laikā
    -0.18
     avulla
    -0.18
    ResumeLayout
    -0.18
    			
    -0.18
    		
    -0.18
     atlik
    -0.18
    -0.18
    POSITIVE LOGITS
    Hentet
    0.40
    setVerticalGroup
    0.40
    الحياه
    0.39
     nakalista
    0.39
    KommentareTeilen
    0.38
    Ecotoxicity
    0.37
     initComponents
    0.37
     հղումներ
    0.37
    يكب
    0.37
    }-*/;
    0.36
    Activations Density 0.078%

    No Known Activations