© 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. 11420
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical sequences and references related to submissions and documentation

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

    legal cases (Id.)

    np_acts-logits-general · gemini-2.0-flash

    legal cases and due 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
     Commencez
    -0.69
     CanadaChoose
    -0.58
    complexContent
    -0.57
    ۱
    -0.55
    ftagPool
    -0.55
     مُعرِّف
    -0.53
    textAppearance
    -0.50
     TType
    -0.49
     typelib
    -0.49
     five
    -0.48
    POSITIVE LOGITS
     utafitiHapana
    0.72
    postsleuth
    0.68
     ioutil
    0.61
    StoryboardSegue
    0.61
    XmlAccessType
    0.60
    SBATCH
    0.59
    hundred
    0.58
    cadilly
    0.57
    ThroughAttribute
    0.57
    (&:
    0.56
    Activations Density 0.744%

    No Known Activations