Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1668
    Prev
    Next
    INDEX
    Explanations

    terms related to touch and tactile interactions

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

    "touch" or its variations

    np_acts-logits-general · gemini-2.0-flash

    touch-screen interfaces and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.53
    CDCl
    -0.52
     nakalista
    -0.52
     scolaires
    -0.51
     chimique
    -0.50
     littéraire
    -0.50
     abel
    -0.49
     pourrais
    -0.48
    瘍
    -0.48
     Reverso
    -0.47
    POSITIVE LOGITS
     TOUCH
    1.38
     Touch
    1.38
     touch
    1.29
    TOUCH
    1.20
     touches
    1.18
    touches
    1.15
    Touch
    1.13
    touch
    1.12
    touched
    1.11
     touched
    1.05
    Activations Density 0.080%

    No Known Activations