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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5334
    Prev
    Next
    INDEX
    Explanations

    attends to the conjunctions from various artists or titles mentioned earlier in the sequence

    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
    1:0.08
    2:0.09
    3:0.06
    4:0.09
    5:0.02
    6:0.22
    7:0.33
    Negative Logits
     ujednoznacz
    -0.42
    MigrationBuilder
    -0.41
    তথ্যসূত্র
    -0.39
    CloseOperation
    -0.37
    BeginContext
    -0.37
     للمعارف
    -0.36
    SourceChecksum
    -0.35
    Autoritní
    -0.34
     NgModule
    -0.34
    TagHelper
    -0.34
    POSITIVE LOGITS
    bollah
    0.26
     autobio
    0.26
     ISTAT
    0.25
     villas
    0.25
    Interactive
    0.25
     interactive
    0.25
    isto
    0.24
    limit
    0.24
    IMF
    0.24
    fold
    0.24
    Activations Density 0.208%

    No Known Activations