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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1785
    Prev
    Next
    INDEX
    Explanations

    programming language elements related to function definitions and conditional checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
     dar
    -0.52
     "":
    -0.46
     Löwen
    -0.44
    gemeinschaft
    -0.43
     linh
    -0.43
    ({_
    -0.42
     Dark
    -0.42
     Darts
    -0.41
    json
    -0.41
     ور
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    1.05
     فريبيس
    1.05
     صوتيه
    1.02
     незавершена
    0.86
     StringTokenizer
    0.81
     AssemblyCulture
    0.76
     الرياضيه
    0.76
     jScrollPane
    0.74
    NOPQRST
    0.71
     utafitiHapana
    0.70
    Activations Density 0.750%

    No Known Activations