© 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. 82259
    Prev
    Next
    INDEX
    Explanations

    Java programming language elements, particularly import statements

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

    java io imports

    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
     compresión
    -0.44
     defectos
    -0.41
     contraintes
    -0.40
     haupts
    -0.39
    endaftar
    -0.39
     modalidad
    -0.38
     tránsito
    -0.38
    routeProvider
    -0.36
     Konsequ
    -0.36
     areia
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.73
     المعيارى
    0.66
     يتيمه
    0.65
     виправивши
    0.58
     насељу
    0.56
     OMITBAD
    0.56
     EconPapers
    0.55
     nakalista
    0.54
    thâu
    0.53
     Signalez
    0.51
    Activations Density 0.011%

    No Known Activations