© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6174
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or ports

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

    "Port" or "port" (often capitalized)

    np_acts-logits-general · gemini-2.0-flash

    portmanteau constructions and related words

    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
     صوتيه
    -0.87
     beginnetje
    -0.80
    AndroidJUnit
    -0.75
    SaveChangesAsync
    -0.70
    HasAnnotation
    -0.69
    NUMX
    -0.69
    ⤹
    -0.69
    apimachinery
    -0.67
    حياته
    -0.66
     Réponses
    -0.66
    POSITIVE LOGITS
    manteau
    0.70
     wine
    0.58
    folios
    0.57
     Ports
    0.56
     PORT
    0.55
    folium
    0.55
    rayed
    0.53
    mouth
    0.53
    foli
    0.53
     Port
    0.52
    Activations Density 0.080%

    No Known Activations