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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14114
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to semiconductor devices and methods

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

    numeric year references, particularly those in academic citations and bibliographic entries.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    year references and date-related numerical sequences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.71
    لينكات
    -0.61
    関する
    -0.55
     bab
    -0.51
    AccessorTable
    -0.49
     sl
    -0.49
    Portale
    -0.49
    катерина
    -0.49
     Campan
    -0.48
     ti
    -0.48
    POSITIVE LOGITS
     Infórmanos
    0.44
    AndEndTag
    0.43
     himſelf
    0.43
     dimaksud
    0.41
    midler
    0.40
     njego
    0.40
     alemana
    0.40
     misalnya
    0.40
     miejsco
    0.39
     varandra
    0.39
    Activations Density 0.384%

    No Known Activations