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. 307
    Prev
    Next
    INDEX
    Explanations

    attends to opening curly brackets from closing curly brackets

    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
    1:0.70
    2:0.04
    3:0.02
    4:0.03
    5:0.05
    6:0.03
    7:0.07
    Negative Logits
     {
    -0.74
    <eos>
    -0.67
     }
    -0.55
    }
    -0.55
    }}}}
    -0.54
     }}}
    -0.53
     *}
    -0.50
     
    -0.49
     *
    -0.47
     }}
    -0.46
    POSITIVE LOGITS
     myſelf
    0.95
     itſelf
    0.93
     Houſe
    0.90
     Anſ
    0.90
     Reſ
    0.90
     houſe
    0.89
     Diſ
    0.85
     pleaſure
    0.85
     Theſe
    0.85
     purpoſe
    0.84
    Activations Density 0.559%

    No Known Activations