© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13366
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical values and classifications in studies

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

    the middle or center position

    np_acts-logits-general · gemini-2.0-flash

    midpoint, middle, intermediate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.64
     pungkas
    -0.52
     zug
    -0.47
    hup
    -0.44
    Glück
    -0.43
    '.
    -0.42
    
    -0.42
    ⎩
    -0.42
     entirely
    -0.42
    ⎣
    -0.42
    POSITIVE LOGITS
     intermediate
    1.18
     mid
    1.14
     middle
    1.13
    middle
    1.07
    intermediate
    1.06
     Intermediate
    1.02
    Mid
    1.01
    mid
    1.00
     Mid
    0.97
    Intermediate
    0.95
    Activations Density 0.718%

    No Known Activations