© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12600
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming issues and their associated configurations

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

    followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    have possession or become

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⤹
    -0.51
     հղումներ
    -0.50
    Hentet
    -0.47
    OGND
    -0.47
     Efq
    -0.46
    ácara
    -0.45
     *++
    -0.44
    Попис
    -0.44
     yyr
    -0.44
     künst
    -0.42
    POSITIVE LOGITS
     possess
    0.54
     have
    0.49
     got
    0.48
     become
    0.46
     had
    0.43
    PerformLayout
    0.43
     became
    0.43
    UnknownFieldSet
    0.42
     posses
    0.42
     able
    0.41
    Activations Density 1.265%

    No Known Activations