© 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. 16-GEMMASCOPE-RES-16K
    6. 5441
    Prev
    Next
    INDEX
    Explanations

    URLs related to video content

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

    YouTube links or mentions

    np_acts-logits-general · gemini-2.0-flash

    youtube watch links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -0.69
    rungsseite
    -0.61
    readAs
    -0.60
    spaceBetween
    -0.59
    Хьажоргаш
    -0.58
     IBOutlet
    -0.55
    ngdoc
    -0.53
    Externé
    -0.53
    agar
    -0.52
    zzard
    -0.52
    POSITIVE LOGITS
    youtube
    0.87
    outube
    0.85
     youtube
    0.83
    Youtube
    0.79
     Youtube
    0.78
    YouTube
    0.76
     YouTube
    0.70
     YOUTUBE
    0.67
    YOUTUBE
    0.66
     Playlist
    0.65
    Activations Density 0.043%

    No Known Activations