© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9152
    Prev
    Next
    INDEX
    Explanations

    conditional and procedural phrases primarily related to instructions or guidance

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

    Mathematical or programming expressions

    np_acts-logits-general · gemini-2.0-flash

    ":" followed by Accounts

    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
     ("
    -0.69
     (“
    -0.66
     (~
    -0.65
     („
    -0.63
     (
    -0.63
     (>
    -0.61
     (&
    -0.58
     "
    -0.53
     (‘
    -0.51
    ACHUSET
    -0.51
    POSITIVE LOGITS
    inaudible
    0.44
     tady
    0.43
    colgroup
    0.43
    etera
    0.42
     cetera
    0.41
     Mawr
    0.41
    ofollow
    0.41
    alition
    0.40
     вот
    0.40
    esModule
    0.40
    Activations Density 0.135%

    No Known Activations