© 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. 9236
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or functions related to computer programming and data processing

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

    Appears after letters "ne"

    np_acts-logits-general · gemini-2.0-flash

    ne or noun endings

    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
    tas
    -0.58
     StatelessWidget
    -0.55
     Suche
    -0.54
    InitStruct
    -0.54
    toMatch
    -0.52
    SUITE
    -0.51
    typer
    -0.51
    da
    -0.50
    ا
    -0.49
     conter
    -0.49
    POSITIVE LOGITS
    nnnn
    1.07
    nnn
    1.06
     Dn
    1.05
     BN
    0.95
     Cn
    0.91
     Pn
    0.91
     Bn
    0.91
     Fn
    0.90
     GN
    0.90
     Vn
    0.90
    Activations Density 0.868%

    No Known Activations