© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2968
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the initiation of actions or processes

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

    "starts" or "started" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    starting an action or process

    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
     continued
    -0.88
    continuing
    -0.86
     continuance
    -0.86
     continuation
    -0.85
    continued
    -0.84
     continuare
    -0.84
    
    -0.83
     continuing
    -0.77
    httphttps
    -0.76
     Continuing
    -0.75
    POSITIVE LOGITS
    le
    0.53
    mybatisplus
    0.50
     EconPapers
    0.50
     work
    0.47
    )$/,
    0.46
     process
    0.45
    led
    0.45
     suspect
    0.44
     wonder
    0.44
     play
    0.43
    Activations Density 0.125%

    No Known Activations