© 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-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13214
    Prev
    Next
    INDEX
    Explanations

    chemical compounds or abbreviations related to chemical formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 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
    lccccc
    -0.50
    Connell
    -0.48
    ldquo
    -0.48
    hspace
    -0.47
    bleau
    -0.47
     Crusoe
    -0.47
    RESOURCE
    -0.46
    rzost
    -0.46
    issipp
    -0.44
    nls
    -0.44
    POSITIVE LOGITS
    ey
    0.86
    yyyy
    0.84
    yy
    0.84
     Dy
    0.83
     Ty
    0.82
     Ky
    0.80
     Zy
    0.80
     Gy
    0.79
    ry
    0.78
    proy
    0.78
    Activations Density 0.696%

    No Known Activations