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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 43213
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "mm" and related technical terms from code snippets or references in programming contexts

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

    UI event value changed

    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
    EReference
    -0.55
    ={({
    -0.49
     henvisninger
    -0.48
     AppCompatTheme
    -0.46
    EnumMember
    -0.45
    Демографія
    -0.45
    lorette
    -0.44
     Roskov
    -0.43
    lüğ
    -0.43
    icolon
    -0.43
    POSITIVE LOGITS
    ByUsername
    1.41
     BaseController
    1.37
    BaseController
    0.95
     EconPapers
    0.85
    ByUserId
    0.82
    TestBase
    0.81
    ByEmail
    0.79
    pulumi
    0.77
     оригіналу
    0.62
     BaseModel
    0.59
    Activations Density 0.001%

    No Known Activations