© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 123659
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to conditional statements and directional commands

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

    direction 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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    GEBURTSDATUM
    -0.77
    ViewFeatures
    -0.69
    setViewportView
    -0.68
     препратки
    -0.68
    ISupport
    -0.68
    ConstraintMaker
    -0.66
     resourceCulture
    -0.66
    #+#
    -0.64
     CreateTagHelper
    -0.60
    principalTable
    -0.59
    POSITIVE LOGITS
     perpendicular
    0.44
     direction
    0.42
    LabelTagHelper
    0.41
    Direction
    0.38
     déplacement
    0.36
    方向
    0.35
     travel
    0.32
    direction
    0.32
     Styles
    0.32
     movement
    0.31
    Activations Density 0.006%

    No Known Activations