© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14070
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to technical specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.51
     OFDb
    -0.44
     localObject
    -0.40
    ErrUnexpectedEOF
    -0.36
     already
    -0.36
    already
    -0.35
    HasForeignKey
    -0.35
    thus
    -0.35
     itself
    -0.34
    itself
    -0.34
    POSITIVE LOGITS
     мәкал
    0.65
     Numerade
    0.60
     ब्रेकडाउन
    0.59
    enumi
    0.56
    참고
    0.52
    PreferredItem
    0.50
     forState
    0.50
    PMailer
    0.46
    úrese
    0.45
    couz
    0.45
    Activations Density 1.740%

    No Known Activations