© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13574
    Prev
    Next
    INDEX
    Explanations

    technical terms related to algorithms and programming

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

    tokens containing the “um” syllable or related vowel+m sequences (e.g., -um/-im/-em/-ism), including standalone filler uses and within longer words or abbreviations.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.85
    a
    -0.71
    Kariera
    -0.64
    edale
    -0.63
    o
    -0.62
    liothèque
    -0.62
     برانيه
    -0.59
    collate
    -0.59
    RequiresApi
    -0.59
    stle
    -0.58
    POSITIVE LOGITS
    mers
    1.05
     JAM
    1.01
     Erm
    1.01
    HAM
    1.00
     SPM
    1.00
     JIM
    1.00
     Bm
    1.00
     HEM
    0.99
     BBM
    0.98
     BEM
    0.98
    Activations Density 1.425%

    No Known Activations