Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 10544
    Prev
    Next
    INDEX
    Explanations

    actions related to data manipulation and transformation in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    …
    -0.52
    ConstraintMaker
    -0.50
    createStatement
    -0.48
    BaseEntity
    -0.46
     colorWith
    -0.46
    migrationBuilder
    -0.46
     للمعارف
    -0.45
    splitlines
    -0.45
    UserScript
    -0.45
    CrossRef
    -0.45
    POSITIVE LOGITS
     ulang
    0.83
    setVerticalGroup
    0.77
     незавершена
    0.76
    GOTREF
    0.74
    ModelSerializer
    0.74
     båda
    0.68
     dulu
    0.67
     proprement
    0.67
    تقاوى
    0.67
    HomeAsUp
    0.66
    Activations Density 0.591%

    No Known Activations