© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7104
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and data structure operations

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

    Code-like terms, often followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    code/data entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.75
    WithIOException
    -0.68
    存于互联网档案馆
    -0.64
    tagHelperRunner
    -0.59
    WriteTagHelper
    -0.53
    ConstraintMaker
    -0.52
    awtextra
    -0.50
    AnimationsModule
    -0.49
    MessageOf
    -0.48
    BagLayout
    -0.47
    POSITIVE LOGITS
     didik
    0.45
    ffè
    0.42
    poli
    0.41
    tanleria
    0.39
    skie
    0.38
    rientes
    0.38
     Dessa
    0.37
    новништво
    0.37
    relli
    0.36
    hilangan
    0.36
    Activations Density 1.109%

    No Known Activations