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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4174
    Prev
    Next
    INDEX
    Explanations

    terms related to velocity and speed

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

    Tokens starting with "vel" or related to velocity

    np_acts-logits-general · gemini-2.0-flash

    vel, velocity, velvety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ideae
    -0.45
    rsiniz
    -0.45
    basicConfig
    -0.40
    hdashline
    -0.39
     cuad
    -0.38
    AnchorStyles
    -0.37
     extérieurs
    -0.37
    ďaka
    -0.35
     prakti
    -0.34
     Constitucional
    -0.34
    POSITIVE LOGITS
    évaluateur
    0.55
     Vel
    0.54
     Chwiliwch
    0.54
     VEL
    0.53
    Vel
    0.52
    المناصب
    0.50
    vele
    0.48
    Velocity
    0.47
     Velocity
    0.47
     يتيمه
    0.46
    Activations Density 0.089%

    No Known Activations