Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6383
    Prev
    Next
    INDEX
    Explanations

    attends to empty or minimal tokens from any token containing content

    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
    0:0.10
    1:0.12
    2:0.25
    3:0.08
    4:0.07
    5:0.08
    6:0.10
    7:0.15
    Negative Logits
    ########.
    -0.36
     beginnetje
    -0.35
    TestingModule
    -0.35
    GenerationType
    -0.33
    principalTable
    -0.30
     @"/
    -0.30
     发表于
    -0.30
     GenerationType
    -0.29
    IUrlHelper
    -0.27
    SharedDtor
    -0.27
    POSITIVE LOGITS
     Aks
    0.34
    AndWait
    0.31
    Aks
    0.29
     Cze
    0.29
     allu
    0.29
    ʖ
    0.29
    })]
    0.27
     naw
    0.27
     Jove
    0.27
     Borel
    0.26
    Activations Density 0.001%

    No Known Activations