Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7877
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or coding in JavaScript

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

    French/Spanish/Portuguese words

    np_acts-logits-general · gemini-2.0-flash

    French and Spanish pronouns and 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
    TagMode
    -0.60
     հղումներ
    -0.60
    Autoritní
    -0.52
    ChildScrollView
    -0.52
    ArrowToggle
    -0.51
    verwijspagina
    -0.51
     Wicidata
    -0.51
    Referanser
    -0.51
     كومونز
    -0.51
     consultato
    -0.49
    POSITIVE LOGITS
    ității
    0.48
     has
    0.48
     is
    0.47
     mempunyai
    0.46
     possesses
    0.46
     autoridad
    0.44
     was
    0.44
    서는
    0.43
    zelf
    0.42
     sendi
    0.42
    Activations Density 0.078%

    No Known Activations