© 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. 15839
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding and technical instructions

    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
     kasarigan
    -0.61
    ConstraintMaker
    -0.56
     BrowserModule
    -0.56
    principalColumn
    -0.54
    TemporalType
    -0.53
    PropertyChanging
    -0.52
    principalTable
    -0.52
     criatura
    -0.52
    IntoConstraints
    -0.51
    oredCriteria
    -0.51
    POSITIVE LOGITS
     flo
    0.41
     Invisible
    0.39
     reg
    0.39
     Cont
    0.38
    LookAnd
    0.37
     dummy
    0.36
     custom
    0.36
    SneakyThrows
    0.36
     Bij
    0.36
     cu
    0.36
    Activations Density 0.686%

    No Known Activations