© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 18517
    Prev
    Next
    INDEX
    Explanations

    instances related to the "sm" (streaming or small memory) context, often indicating usage in programming or technical discussions

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

    sm and smart variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.39
    ibase
    -0.39
    liferay
    -0.39
    ├──
    -0.39
    yeur
    -0.38
    íte
    -0.37
    podar
    -0.37
     duce
    -0.37
    oar
    -0.37
    BASEPATH
    -0.36
    POSITIVE LOGITS
     sm
    2.72
     Smar
    1.45
    smar
    1.27
    Smar
    1.27
     Sm
    1.19
     smar
    1.10
     Smy
    1.10
    Sm
    1.06
     SM
    0.98
     smart
    0.97
    Activations Density 0.001%

    No Known Activations