© 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. 5508
    Prev
    Next
    INDEX
    Explanations

    terms related to growth metrics and performance indicators

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

    "growth"

    np_acts-logits-general · gemini-2.0-flash

    growth rate and potential

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    éndole
    -0.58
    Composable
    -0.57
    __*/
    -0.55
    cang
    -0.52
     صوتيه
    -0.52
    (&$
    -0.50
    albero
    -0.50
     quæ
    -0.50
     =>
    -0.50
    contentLoaded
    -0.49
    POSITIVE LOGITS
     spurt
    0.95
     rate
    0.90
     trajectory
    0.79
     rates
    0.72
     acceleration
    0.70
     Acceleration
    0.70
     trajectories
    0.70
     Rate
    0.68
     RATE
    0.67
     prospects
    0.65
    Activations Density 0.163%

    No Known Activations