© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12980
    Prev
    Next
    INDEX
    Explanations

    terms related to climbing and playground equipment

    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
    PhysRev
    -0.46
     unicornio
    -0.45
    Parcelize
    -0.44
     MotionEvent
    -0.44
    GenerationType
    -0.43
     Parcelable
    -0.40
    UnusedPrivate
    -0.39
     postIndex
    -0.38
    miot
    -0.38
     licorne
    -0.38
    POSITIVE LOGITS
     climbing
    1.13
     Climbing
    1.02
     climbers
    0.94
    Climbing
    0.93
     climber
    0.89
     climb
    0.88
    climbing
    0.87
     climbs
    0.86
     Climb
    0.83
    Climb
    0.81
    Activations Density 0.074%

    No Known Activations