© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 10486
    Prev
    Next
    INDEX
    Explanations

    instances of the word "touch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ätzt
    -0.50
     schlimm
    -0.47
     غذایی
    -0.46
     groß
    -0.45
    ferien
    -0.45
    institut
    -0.44
    közi
    -0.44
    instance
    -0.44
     obicei
    -0.43
    éről
    -0.43
    POSITIVE LOGITS
     TOUCH
    1.69
     Touch
    1.68
     touch
    1.65
    TOUCH
    1.56
     touches
    1.46
    touch
    1.42
    Touch
    1.42
    touched
    1.34
     touched
    1.33
     touching
    1.31
    Activations Density 0.098%

    No Known Activations