© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to power ratings and electrical components

    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
     ύ
    -0.56
    RegressionTest
    -0.56
    engk
    -0.53
    ruptedException
    -0.53
    ExecuteNonQuery
    -0.52
    UnknownFieldSet
    -0.47
    كال
    -0.47
     presencia
    -0.47
     navideñas
    -0.46
     PRINCIP
    -0.46
    POSITIVE LOGITS
     rated
    1.26
    rated
    1.07
     Rated
    1.04
    Rated
    0.96
     rating
    0.95
     nominal
    0.94
    nominal
    0.88
     max
    0.86
     ratings
    0.83
     Nominal
    0.82
    Activations Density 0.420%

    No Known Activations