Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1688
    Prev
    Next
    INDEX
    Explanations

    the presence of formatting or markup indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.56
    PreferredItem
    -0.55
    ();)
    -0.55
    ']):
    -0.52
    ($__
    -0.52
    zji
    -0.51
    マン
    -0.50
    attle
    -0.50
    MAN
    -0.49
    AddAttribute
    -0.48
    POSITIVE LOGITS
     rzecz
    0.63
    enumi
    0.61
     portuguesa
    0.60
    \}\\
    0.58
     дописавши
    0.57
    zzleHttp
    0.57
    KEYCODE
    0.57
     ferons
    0.55
     humaines
    0.54
     مشارکت‌کنندگان
    0.54
    Activations Density 0.028%

    No Known Activations