© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 6806
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and syntax structures

    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
    Personensuche
    -0.51
    parsedMessage
    -0.51
     stater
    -0.50
    atili
    -0.49
     Ashford
    -0.48
    CDCl
    -0.46
    altham
    -0.46
    úsqueda
    -0.45
     inoxydable
    -0.44
     Whitley
    -0.43
    POSITIVE LOGITS
    foo
    1.40
     foo
    1.30
    Foo
    1.29
     Foo
    1.20
    some
    1.11
    FOO
    1.07
     some
    1.06
    foobar
    1.06
    Some
    1.01
     another
    0.97
    Activations Density 1.221%

    No Known Activations