© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4508
    Prev
    Next
    INDEX
    Explanations

    HTML or web-related elements and snippets, often related to structure and links

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

    Markdown formatting: badges, links, images

    np_acts-logits-general · gemini-2.0-flash

    badges and closing tags</p>

    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
    PosX
    -0.38
     Exacts
    -0.35
     ioutil
    -0.35
     “
    -0.34
    ")==
    -0.32
    NSNotification
    -0.31
     [],
    -0.31
    AndSet
    -0.31
    $/,
    -0.31
     timedelta
    -0.31
    POSITIVE LOGITS
     resourceCulture
    1.18
    httphttps
    0.75
     <<<<<<<<<<<<<<
    0.75
    KommentareTeilen
    0.71
    expandindo
    0.70
    richTextPanel
    0.70
    évaluateur
    0.69
     propOrder
    0.63
    QMetaType
    0.62
    IUrlHelper
    0.61
    Activations Density 1.297%

    No Known Activations