© 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. 31-GEMMASCOPE-RES-16K
    11. 3538
    Prev
    Next
    INDEX
    Explanations

    references to the most recent updates, news, or information on various topics

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

    the word "latest" and related temporal descriptors indicating recency or current status.

    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
     recentemente
    -0.37
     recently
    -0.35
     second
    -0.33
     originalmente
    -0.33
     originally
    -0.31
     tố
    -0.31
     earlier
    -0.31
     first
    -0.30
     Actualmente
    -0.30
     actualmente
    -0.30
    POSITIVE LOGITS
     iteration
    1.23
     iterations
    1.11
     edition
    1.08
     instalment
    1.07
     installment
    1.05
     editions
    1.03
     incarnation
    0.96
     installments
    0.92
     instalments
    0.90
    edition
    0.89
    Activations Density 0.449%

    No Known Activations