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. 4356
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles of individuals

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

    Follows "Mr." or initials

    np_acts-logits-general · gemini-2.0-flash

    Grissom Giunta Papadopoulos Kukulga

    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
    Carreira
    -0.43
    FromNib
    -0.41
     UserDao
    -0.40
    zbęd
    -0.40
     cellar
    -0.39
     kapturem
    -0.39
    ighorn
    -0.38
    Discografia
    -0.38
    diyesi
    -0.38
    ioterapia
    -0.37
    POSITIVE LOGITS
    SourceChecksum
    0.63
    AddTagHelper
    0.63
    AISSEE
    0.59
    ########.
    0.59
     Paglinawan
    0.52
    RegressionTest
    0.52
    @[+][
    0.52
    Hentet
    0.47
     المعيارى
    0.46
    httphttps
    0.45
    Activations Density 0.315%

    No Known Activations