© 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. 35-GEMMASCOPE-RES-16K
    11. 12712
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to functions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.08
     utafitiHapana
    -0.84
    Tikang
    -0.66
     Chwiliwch
    -0.66
    Билгалдахарш
    -0.65
     estekak
    -0.65
    verwijspagina
    -0.64
     ujednoznacz
    -0.63
    yntax
    -0.63
     ModelExpression
    -0.62
    POSITIVE LOGITS
    uxxxx
    0.35
     k
    0.32
     $\
    0.31
     x
    0.30
     X
    0.29
     p
    0.29
     z
    0.28
     n
    0.28
     y
    0.28
     f
    0.27
    Activations Density 8.690%

    No Known Activations