© 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. 10556
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases that indicate significance or importance in various contexts

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

    "The" or "a" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    key component or aspect

    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
    UserScript
    -0.66
     initComponents
    -0.58
    httphttps
    -0.56
     <>",
    -0.54
    astéroïdes
    -0.54
    GOTREF
    -0.52
    Clik
    -0.52
    VolleyError
    -0.52
    baomidou
    -0.51
    PyExc
    -0.51
    POSITIVE LOGITS
     proof
    0.69
     synonym
    0.67
     basis
    0.64
    stawa
    0.62
    evidence
    0.62
     key
    0.61
     aggiunto
    0.60
     evidence
    0.60
     source
    0.60
     backbone
    0.60
    Activations Density 0.220%

    No Known Activations