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. 6453
    Prev
    Next
    INDEX
    Explanations

    attends to "mbox" from "in"

    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
    0:0.07
    1:0.09
    2:0.06
    3:0.04
    4:0.16
    5:0.46
    6:0.04
    7:0.05
    Negative Logits
    till
    -0.26
    1
    -0.26
     Maris
    -0.25
    ExtendWith
    -0.24
    is
    -0.24
     compris
    -0.23
     Weise
    -0.23
    ag
    -0.23
     abord
    -0.23
    alt
    -0.23
    POSITIVE LOGITS
    ieteur
    0.41
     layui
    0.38
    RectangleBorder
    0.36
    PRINTF
    0.35
     = 
    0.34
    poptotic
    0.33
    PerformLayout
    0.33
    modore
    0.33
    Swal
    0.33
    enumii
    0.33
    Activations Density 0.252%

    No Known Activations