© 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. 33-GEMMASCOPE-RES-16K
    11. 10995
    Prev
    Next
    INDEX
    Explanations

    references to incomplete or missing information in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.38
     '{@
    -0.37
     muualla
    -0.36
    böz
    -0.36
    DECREF
    -0.36
    NewLabel
    -0.36
    glBindTexture
    -0.35
    isdir
    -0.32
    DataInputStream
    -0.32
    glMatrixMode
    -0.32
    POSITIVE LOGITS
     filling
    3.45
     fill
    3.36
     fills
    3.13
     Fill
    3.11
     Filling
    3.09
    Filling
    2.97
    Fill
    2.95
     filled
    2.92
    fill
    2.91
    filling
    2.86
    Activations Density 0.830%

    No Known Activations