© 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. 16-GEMMASCOPE-RES-16K
    11. 6801
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that convey a beginning or introductory context

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

    Code, genetics, or power

    np_acts-logits-general · gemini-2.0-flash

    genome, gnus, seats

    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
     Мексичка
    -0.71
    Lähteet
    -0.68
    Hentet
    -0.63
     EnglishChoose
    -0.61
    脚注の使い方
    -0.61
    ContentAsync
    -0.59
    typeparam
    -0.57
    "];
    -0.57
    }))
    -0.57
    MemoryWarning
    -0.57
    POSITIVE LOGITS
    ̣c
    0.56
     …
    0.53
    +:+
    0.49
    StoreMessageInfo
    0.49
    â
    0.47
     galletas
    0.46
     تانيه
    0.45
    ometre
    0.45
    writeField
    0.45
    frid
    0.44
    Activations Density 0.379%

    No Known Activations