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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7214
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and relationships in polynomial space

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

    Degree of polynomial

    np_acts-logits-general · gemini-2.0-flash

    mathematical degree, period, sequence, multiplicity, pairs, volume

    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
    ########.
    -0.48
    mical
    -0.43
    eled
    -0.41
    pions
    -0.41
    IUrlHelper
    -0.40
    gonic
    -0.40
    xic
    -0.40
    IsMutable
    -0.40
    __*/
    -0.39
    edicated
    -0.39
    POSITIVE LOGITS
    sidemargin
    0.44
    AndEndTag
    0.44
     musul
    0.41
     delà
    0.40
     nonUne
    0.39
    Tikang
    0.39
     Corée
    0.38
    etcode
    0.37
     invokingState
    0.37
    ksesta
    0.37
    Activations Density 2.013%

    No Known Activations