© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 425
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of processes related to mechanics or structural changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Movement, rotation, or displacement

    np_acts-logits-general · gemini-2.0-flash

    rotation and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vuur
    -0.37
     breakdowns
    -0.36
     exited
    -0.35
    tisan
    -0.35
     Exponential
    -0.35
    uterie
    -0.34
     läh
    -0.34
    WriteTagHelper
    -0.34
    rittura
    -0.34
     generative
    -0.34
    POSITIVE LOGITS
    SourceChecksum
    0.63
    ChildScrollView
    0.61
     AssemblyCulture
    0.59
    DrawerToggle
    0.53
    WireFormatLite
    0.52
    setVerticalGroup
    0.51
    horabuena
    0.51
     relocation
    0.49
    GOTREF
    0.49
     mover
    0.49
    Activations Density 0.653%

    No Known Activations