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. 6141
    Prev
    Next
    INDEX
    Explanations

    attends to the validation status of tokens marked as "NULL" from tokens marked as "NOT NULL."

    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
    0:0.06
    1:0.12
    2:0.06
    3:0.05
    4:0.21
    5:0.37
    6:0.04
    7:0.06
    Negative Logits
     estekak
    -0.39
    στό
    -0.32
    出版年
    -0.32
    RenderAtEndOf
    -0.32
     فريبيس
    -0.30
    NOPQRST
    -0.29
    rinth
    -0.28
    LError
    -0.28
     يتيمه
    -0.27
    erba
    -0.27
    POSITIVE LOGITS
    zeciw
    0.29
    UnusedPrivate
    0.26
    AnchorStyles
    0.23
    ChildScrollView
    0.23
    IBOutlet
    0.23
    المشاركات
    0.23
    ForValue
    0.23
    <bos>
    0.23
    EndGlobalSection
    0.22
     gobier
    0.21
    Activations Density 0.036%

    No Known Activations