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. 5774
    Prev
    Next
    INDEX
    Explanations

    attends to regional descriptors marked by 'British', 'Indian', 'Iranian', and 'Western' from 'style' or similar descriptors

    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
    0:0.29
    1:0.25
    2:0.17
    3:0.06
    4:0.05
    5:0.02
    6:0.05
    7:0.07
    Negative Logits
    LookAnd
    -0.34
     متعلقه
    -0.29
     EconPapers
    -0.29
    Koordinaten
    -0.26
    ysław
    -0.26
    errHandler
    -0.25
    Région
    -0.25
    botas
    -0.24
    MLLoader
    -0.24
    themselves
    -0.23
    POSITIVE LOGITS
    ]--;
    0.28
    ArgsConstructor
    0.24
    QMetaType
    0.23
    FailureListener
    0.22
    RUnlock
    0.22
     ſhould
    0.21
    ecore
    0.21
    UnknownFieldSet
    0.20
     ISNI
    0.20
    gså
    0.20
    Activations Density 0.487%

    No Known Activations