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-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 13
    Prev
    Next
    INDEX
    Explanations

    attends to application names from the corresponding build or configuration tokens

    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
    0:0.02
    1:0.05
    2:0.06
    3:0.05
    4:0.07
    5:0.10
    6:0.59
    7:0.04
    Negative Logits
    }}$
    -0.67
    }},
    -0.66
    }
    -0.66
    }})
    -0.65
    )}
    -0.65
    }}
    -0.65
    "},
    -0.64
    }}$.
    -0.63
    ]}
    -0.61
    )})
    -0.61
    POSITIVE LOGITS
     myſelf
    0.79
     itſelf
    0.78
     pleaſure
    0.76
     himſelf
    0.75
     purpoſe
    0.68
     themſelves
    0.67
     greateſt
    0.66
     Anſ
    0.65
     Jefus
    0.64
     houſe
    0.64
    Activations Density 0.083%

    No Known Activations