© 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. 1-GEMMASCOPE-RES-16K
    11. 10165
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'kick' or actions that invoke a strong impact or response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.59
     utafitiHapana
    -0.58
    domada
    -0.56
    ReusableCell
    -0.46
    GMENT
    -0.46
     OnInit
    -0.46
     createState
    -0.44
    ographer
    -0.44
     asciug
    -0.43
    narr
    -0.43
    POSITIVE LOGITS
     realize
    0.79
     realizes
    0.75
     realized
    0.73
     kicks
    0.69
     kicked
    0.69
     kick
    0.67
     kicking
    0.58
     realizing
    0.58
     realise
    0.58
    nothing
    0.58
    Activations Density 0.220%

    No Known Activations