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. 0-GEMMASCOPE-ATT-16K
    6. 165
    Prev
    Next
    INDEX
    Explanations

    attends to the term "throughout" from various contexts to the associated location or time-related terms

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.05
    1:0.04
    2:0.03
    3:0.02
    4:0.59
    5:0.15
    6:0.04
    7:0.04
    Negative Logits
    ()]);
    -0.41
    }';
    -0.36
    تفصیلات
    -0.35
    ("]");
    -0.35
    mortar
    -0.34
     ]
    
    -0.33
    OGND
    -0.33
    ?
    
    -0.32
    󠁢
    -0.32
     stronę
    -0.31
    POSITIVE LOGITS
     puissiez
    0.54
    complexType
    0.51
     AttributeSet
    0.49
    HttpFoundation
    0.49
    Lycka
    0.46
     sacco
    0.44
     magasiner
    0.44
    enumi
    0.44
     GridLayout
    0.44
     Critic
    0.44
    Activations Density 0.024%

    No Known Activations