© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9765
    Prev
    Next
    INDEX
    Explanations

    verbs and gerunds related to actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    tagHelperRunner
    -0.47
    propTypes
    -0.46
    /*
    -0.39
     erbjud
    -0.38
     piele
    -0.37
     Refined
    -0.36
     potest
    -0.34
    łby
    -0.34
     camada
    -0.34
     acoper
    -0.34
    POSITIVE LOGITS
     defStyleAttr
    0.66
    Rüyada
    0.60
     oneself
    0.60
    protoimpl
    0.56
    yourself
    0.56
    getting
    0.54
    Purchasing
    0.54
    Enjoying
    0.54
    Letting
    0.54
     Playing
    0.54
    Activations Density 0.459%

    No Known Activations