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. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking and food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attends to cooking-related tokens from food preparation actions.

    oai_attention-head · gpt-4o-miniTriggered by @pigeonzow
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.82
    ">:
    -0.76
    المناصب
    -0.63
    ValueStyle
    -0.61
    satunya
    -0.60
    })*/
    -0.59
    +#+#
    -0.58
    WebVitals
    -0.58
     contextLoads
    -0.57
    });*/
    -0.56
    POSITIVE LOGITS
     circular
    0.56
    Circular
    0.55
    ьаж
    0.54
     surla
    0.52
     Circular
    0.51
     glass
    0.50
    circular
    0.49
    anstalt
    0.49
    setzer
    0.49
    GEBURTS
    0.49
    Activations Density 0.300%

    No Known Activations