© 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. 9888
    Prev
    Next
    INDEX
    Explanations

    terms related to non-standard or atypical properties in a technical context

    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
     not
    -0.55
    either
    -0.52
     either
    -0.51
     possibile
    -0.50
    Either
    -0.50
     eventuali
    -0.49
     Either
    -0.49
    not
    -0.49
     läng
    -0.47
    mendation
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.86
    ंदीखरीदारी
    0.58
     destructive
    0.58
     existent
    0.58
     HasFactory
    0.57
     ◄
    0.57
    etheless
    0.56
     obstante
    0.56
    Javadoc
    0.56
    ograms
    0.55
    Activations Density 0.246%

    No Known Activations