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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10368
    Prev
    Next
    INDEX
    Explanations

    programming concepts and structures

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

    Code, filenames, or programming terms

    np_acts-logits-general · gemini-2.0-flash

    software settings and features

    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
     itſelf
    -1.17
     ་་
    -1.10
     myſelf
    -1.05
    存于互联网档案馆
    -1.01
     isNameExpr
    -1.00
     Efq
    -1.00
     }}$}
    -0.99
     $_"
    -0.99
     ſy
    -0.98
    новниш
    -0.98
    POSITIVE LOGITS
    a
    0.51
     i
    0.49
    -
    0.49
     &
    0.49
    이
    0.48
    ®
    0.48
     /
    0.47
     lai
    0.47
    起
    0.47
    «
    0.46
    Activations Density 0.148%

    No Known Activations