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. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3312
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their results

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

    Numbers or values

    np_acts-logits-general · gemini-2.0-flash

    half of quantity/value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.57
    KommentareTeilen
    -0.56
    IVEREF
    -0.53
    DeleteBehavior
    -0.52
    ंदीखरीदारी
    -0.50
    onViewCreated
    -0.48
    ctools
    -0.47
    ]")]
    -0.47
    tisgarh
    -0.44
    Comer
    -0.44
    POSITIVE LOGITS
     half
    0.83
    half
    0.77
    Half
    0.71
     Half
    0.70
    HALF
    0.66
     HALF
    0.65
    一半
    0.65
     lenker
    0.62
    pherals
    0.59
    半
    0.58
    Activations Density 0.425%

    No Known Activations