© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10848
    Prev
    Next
    INDEX
    Explanations

    occurrences of directed actions or interactions involving individuals

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

    direction or movement

    np_acts-logits-general · gemini-2.0-flash

    direction at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.52
     ſtre
    -0.50
    idah
    -0.48
    atos
    -0.48
    bootstrapcdn
    -0.48
     preſent
    -0.47
    ')}
    -0.47
     marginLeft
    -0.47
    "){
    -0.47
     kinematics
    -0.46
    POSITIVE LOGITS
     propOrder
    0.81
     direction
    0.73
    fjspx
    0.72
     للاسماء
    0.69
    expandindo
    0.67
     DIRECTION
    0.66
    direction
    0.65
     my
    0.65
    LookAnd
    0.64
    FunctionFlags
    0.63
    Activations Density 0.087%

    No Known Activations