© 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. 8144
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and experiences related to events over the year

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

    Followed by "great"

    np_acts-logits-general · gemini-2.0-flash

    evaluating periods or events

    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
    tvguidetime
    -0.81
    #+#
    -0.76
    principalColumn
    -0.73
    adaptiveStyles
    -0.70
     cherchés
    -0.68
    ConstraintMaker
    -0.66
    oplayer
    -0.63
    SBATCH
    -0.63
    TemporalType
    -0.59
     WaitForSeconds
    -0.58
    POSITIVE LOGITS
     eventful
    1.26
     productive
    0.93
     memorable
    0.89
     tumultuous
    0.86
     busy
    0.83
     turbulent
    0.83
     fruitful
    0.82
    productive
    0.74
     rough
    0.74
     stressful
    0.73
    Activations Density 0.165%

    No Known Activations