© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5895
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and constructs, particularly focusing on arguments and function definitions

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

    Code snippets with arguments or parameters

    np_acts-logits-general · gemini-2.0-flash

    arguments and inputs

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Rät
    -0.30
    erden
    -0.28
    assertIn
    -0.28
     ripet
    -0.27
    EReference
    -0.27
    くま
    -0.27
     within
    -0.26
     suor
    -0.26
     ú
    -0.26
     racing
    -0.26
    POSITIVE LOGITS
    PathVariable
    0.74
    sidemargin
    0.69
     CallOverrides
    0.60
     parametro
    0.60
     referenties
    0.60
     متعلقه
    0.59
    MultipartFile
    0.57
     ſta
    0.57
    PathParam
    0.57
     faſt
    0.57
    Activations Density 0.773%

    No Known Activations