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. 10-GEMMASCOPE-ATT-16K
    6. 5797
    Prev
    Next
    INDEX
    Explanations

    attends to the second-person pronoun or related terms from third-person pronouns or related terms

    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
    0:0.20
    1:0.11
    2:0.41
    3:0.06
    4:0.05
    5:0.02
    6:0.04
    7:0.07
    Negative Logits
    AddTagHelper
    -0.36
    "}")
    -0.35
    MemoryWarning
    -0.32
    ніципа
    -0.31
    AccessorTable
    -0.30
     weisen
    -0.30
    timmt
    -0.30
    }$.\\
    -0.30
     defStyleAttr
    -0.30
    ChildScrollView
    -0.29
    POSITIVE LOGITS
     conmigo
    0.34
     mourir
    0.31
     față
    0.28
    Salta
    0.28
     comigo
    0.28
    RTGC
    0.28
     mourut
    0.28
     meurt
    0.28
     umani
    0.27
     saites
    0.27
    Activations Density 0.550%

    No Known Activations