© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9619
    Prev
    Next
    INDEX
    Explanations

    occurrences of action verbs and phrases indicating effort or change

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

    Precedes adverbs of degree ("much," "many")

    np_acts-logits-general · gemini-2.0-flash

    lack of anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Occasionally
    -0.67
     occasionally
    -0.61
     Occasionally
    -0.61
     nonetheless
    -0.61
    SOME
    -0.57
    albeit
    -0.55
    somewhere
    -0.53
     alternatively
    -0.53
     tantôt
    -0.51
    UrlResolution
    -0.50
    POSITIVE LOGITS
     much
    1.91
    much
    1.55
     many
    1.42
     muito
    1.40
    Much
    1.40
     very
    1.37
     muchas
    1.36
     mucha
    1.33
     Much
    1.32
     mycket
    1.30
    Activations Density 0.366%

    No Known Activations