© 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. 10790
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions that deal with question parsing and handling

    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
    CopyWith
    -0.52
     AttributeSet
    -0.51
    ConstraintMaker
    -0.49
    esModule
    -0.48
    PhysRev
    -0.44
    XmlAccessType
    -0.43
     framför
    -0.41
    WithIOException
    -0.40
    zwungen
    -0.40
    MethodManager
    -0.39
    POSITIVE LOGITS
     periodi
    0.44
     progre
    0.39
     continúas
    0.39
    StoryboardSegue
    0.39
     updateUser
    0.39
     Савезне
    0.39
    PerformLayout
    0.38
     acum
    0.38
     filtre
    0.37
     tartalomajánló
    0.37
    Activations Density 0.341%

    No Known Activations