© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 3183
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly those related to definitions or notations in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.67
     BoxDecoration
    -0.59
     PublicKey
    -0.58
    Билгалдахарш
    -0.58
    SPATH
    -0.57
    httphttps
    -0.57
    SOUNDBITE
    -0.55
     color
    -0.54
    ंदीखरीदारी
    -0.53
    Ligações
    -0.53
    POSITIVE LOGITS
    ftagPool
    0.59
     crossorigin
    0.52
     Penh
    0.52
    ConstraintMaker
    0.50
    quad
    0.49
    udsman
    0.48
    |$
    0.47
    #+#
    0.47
     Quarte
    0.46
    operatorname
    0.46
    Activations Density 0.170%

    No Known Activations