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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2327
    Prev
    Next
    INDEX
    Explanations

    terms related to file management and directory 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
    독
    -0.50
    ÍAS
    -0.50
    Rüyada
    -0.49
    PasswordEncoder
    -0.46
    readAll
    -0.41
     userSchema
    -0.41
    bine
    -0.41
    YTICAL
    -0.39
     Spiral
    -0.39
     okuyayım
    -0.39
    POSITIVE LOGITS
    ungs
    0.87
    ungen
    0.74
    ung
    0.71
    UNG
    0.71
    SourceChecksum
    0.67
    Datuak
    0.66
    ungsver
    0.65
    bare
    0.64
    Lähteet
    0.63
    ungszeit
    0.63
    Activations Density 0.145%

    No Known Activations