© 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. 33-GEMMASCOPE-RES-16K
    6. 629
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles associated with various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingly
    -0.57
    wander
    -0.45
    lessly
    -0.43
    CreateDate
    -0.43
    givers
    -0.42
    cased
    -0.42
    ably
    -0.41
    Wander
    -0.40
    INGS
    -0.38
    offering
    -0.38
    POSITIVE LOGITS
     techniques
    0.84
     abilities
    0.72
     efforts
    0.72
     capabilities
    0.70
    UrlResolution
    0.70
     activities
    0.67
     exercises
    0.66
     skills
    0.66
     technique
    0.65
    techniques
    0.65
    Activations Density 0.613%

    No Known Activations