© 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. 28-GEMMASCOPE-RES-16K
    11. 5032
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and Java keywords

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

    Followed by "in"

    np_acts-logits-general · gemini-2.0-flash

    diagnoses in

    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
     defaultstate
    -0.77
    __':
    -0.63
    httphttps
    -0.63
    PerformLayout
    -0.60
    ंदीखरीदारी
    -0.60
     TextInputType
    -0.59
    providedIn
    -0.58
     HasFactory
    -0.56
    jsonwebtoken
    -0.56
    enumii
    -0.55
    POSITIVE LOGITS
     Einfluß
    0.36
     Baumann
    0.30
    出自
    0.29
     Better
    0.29
     Geschä
    0.29
     مش
    0.29
    Better
    0.28
    推荐阅读
    0.28
    SUCCEEDED
    0.28
    INTERVAL
    0.27
    Activations Density 0.052%

    No Known Activations