© 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. 8474
    Prev
    Next
    INDEX
    Explanations

    specific job titles and roles in a work context

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

    Followed by commas/punctuation

    np_acts-logits-general · gemini-2.0-flash

    punctuations and separators

    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
     utafitiHapana
    -0.80
     $_-
    -0.77
    <unused52>
    -0.77
    <unused14>
    -0.76
     Infórmanos
    -0.76
    [@BOS@]
    -0.76
    <unused51>
    -0.76
    <unused79>
    -0.76
    <unused28>
    -0.76
    <unused68>
    -0.76
    POSITIVE LOGITS
    ,
    1.64
     ,
    0.53
    ，
    0.50
    、
    0.39
    ،
    0.38
    ,,
    0.34
    .,
    0.32
    -,
    0.31
    ,.
    0.31
     porcelaine
    0.29
    Activations Density 1.065%

    No Known Activations