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. 18-GEMMASCOPE-RES-16K
    6. 8743
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, variables, and expressions associated with equations and functions

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

    Mathematical symbols and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical or scientific text

    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
    ])));
    -0.57
    배
    -0.57
    ]^{-
    -0.55
    multiply
    -0.53
    vine
    -0.53
    cami
    -0.52
     ویکی‌پدیای
    -0.52
    ]<=
    -0.51
    atemala
    -0.51
    GOTREF
    -0.51
    POSITIVE LOGITS
     +
    0.98
    +
    0.91
     plus
    0.90
    +
    0.79
     Meksiku
    0.78
    +\
    0.75
     $+$
    0.73
    +#+
    0.73
    +(
    0.72
     плюс
    0.70
    Activations Density 0.869%

    No Known Activations