© 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. 5370
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to configurations and technology instructions

    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
     les
    -0.78
    mybatisplus
    -0.60
     le
    -0.59
     تضيفلها
    -0.58
    WithIOException
    -0.57
    клопе
    -0.57
    TypedDataSet
    -0.56
    yfik
    -0.53
    bootstrapcdn
    -0.53
    __((
    -0.53
    POSITIVE LOGITS
     gauche
    0.45
    isContained
    0.45
     disambiguazione
    0.45
     Durchmesser
    0.44
     droite
    0.44
     cause
    0.44
    lectual
    0.44
    adone
    0.43
    urtstag
    0.43
     côtés
    0.42
    Activations Density 0.151%

    No Known Activations