© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2052
    Prev
    Next
    INDEX
    Explanations

    verbs related to ongoing action or continuous processes

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

    phrases involving repetitive or continuous actions, like "constantly doing" something.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    StoryboardSegue
    -0.54
    bootstrapcdn
    -0.51
     onPostExecute
    -0.49
    WriteTagHelper
    -0.48
    :✨
    -0.48
     confé
    -0.47
    <_>
    -0.46
    melada
    -0.45
    <mask>
    -0.45
    Personendaten
    -0.45
    POSITIVE LOGITS
     constantly
    1.20
     continually
    1.05
     continuously
    1.05
    不断
    1.00
     continuamente
    0.98
     constantemente
    0.97
    不斷
    0.97
     постоянно
    0.93
    不断的
    0.92
     constant
    0.91
    Activations Density 0.161%

    No Known Activations