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. 6063
    Prev
    Next
    INDEX
    Explanations

    attends to lists or numbered items from subsequent tokens that suggest additional relevant information or actions

    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
    1:0.06
    2:0.06
    3:0.11
    4:0.10
    5:0.02
    6:0.44
    7:0.09
    Negative Logits
    intios
    -0.42
    tonode
    -0.42
     насељу
    -0.40
     Paglinawan
    -0.39
    AutoScaleMode
    -0.37
    AnimationsModule
    -0.36
     MonoBehaviour
    -0.36
     Wicidata
    -0.35
    ########.
    -0.34
     linkovi
    -0.33
    POSITIVE LOGITS
     referrerpolicy
    0.39
     *);
    0.37
    *********/
    0.37
    }>;
    0.35
    ↵
    0.35
    }();
    0.34
    ****/
    0.33
    =?";
    0.32
    ].(
    0.32
    }*/
    
    0.32
    Activations Density 0.625%

    No Known Activations