© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10191
    Prev
    Next
    INDEX
    Explanations

    elements related to project configuration and build management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.62
    queryInterface
    -0.61
    DataContract
    -0.54
    VersionUID
    -0.54
    MongoClient
    -0.53
     offerts
    -0.50
    ölkerung
    -0.50
    caris
    -0.50
    mauri
    -0.50
    MLLoader
    -0.49
    POSITIVE LOGITS
     Build
    0.83
    Build
    0.80
     BUILD
    0.76
     build
    0.76
    build
    0.72
     targets
    0.63
    BUILD
    0.61
     Makefile
    0.60
     tasks
    0.59
     bygge
    0.59
    Activations Density 0.919%

    No Known Activations