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. 10-GEMMASCOPE-ATT-16K
    6. 6577
    Prev
    Next
    INDEX
    Explanations

    attends to any token containing a hyphen or underscore from tokens that denote a file extension or format

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.09
    1:0.10
    2:0.04
    3:0.03
    4:0.27
    5:0.35
    6:0.03
    7:0.05
    Negative Logits
     ]
    
    -0.30
    },[])
    -0.29
     zvuky
    -0.28
    detectChanges
    -0.27
     ")"
    -0.27
    }]
    
    -0.27
     [];
    
    -0.26
    '));
    
    -0.26
    ?")
    -0.26
    "]).
    -0.26
    POSITIVE LOGITS
     felb
    0.29
    Viitteet
    0.29
    AddTagHelper
    0.28
     naselje
    0.27
     OTHERWISE
    0.27
    aup
    0.27
    fahrene
    0.26
     Polsek
    0.26
    vertre
    0.26
     loophole
    0.26
    Activations Density 0.337%

    No Known Activations