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. 1336
    Prev
    Next
    INDEX
    Explanations

    attends to the term "throw" from instances of error-related tokens

    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
    1:0.01
    2:0.09
    3:0.03
    4:0.01
    5:0.00
    6:0.17
    7:0.09
    8:0.01
    9:0.01
    10:0.01
    11:0.02
    12:0.08
    13:0.30
    14:0.07
    15:0.02
    Negative Logits
     Normdatei
    -0.38
    SharedCtor
    -0.36
    ſelf
    -0.31
    fjspx
    -0.30
    verwijspagina
    -0.29
    AndEndTag
    -0.29
     Hauteur
    -0.29
     judiciales
    -0.28
    ſelves
    -0.28
     ſch
    -0.28
    POSITIVE LOGITS
     },
    
    0.35
    '),
    
    0.34
    .*")]
    0.32
    "),
    
    0.32
    '],
    
    0.31
    "];
    
    0.31
    ?
    
    0.31
     })
    
    0.30
     indirect
    0.30
    "]).
    0.30
    Activations Density 0.020%

    No Known Activations