© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16098
    Prev
    Next
    INDEX
    Explanations

    structured data related to reviews or reports

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

    Code or technical language snippets

    np_acts-logits-general · gemini-2.0-flash

    technical documents and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InMillis
    -0.59
     GenerationType
    -0.49
    ceğine
    -0.48
    raš
    -0.48
     NDEBUG
    -0.43
    عين
    -0.43
    InvalidProtocol
    -0.42
     offers
    -0.41
    worfen
    -0.41
     recommendations
    -0.41
    POSITIVE LOGITS
     EconPapers
    1.31
     autorytatywna
    1.21
    rungsseite
    1.09
     beginnetje
    1.05
     Roskov
    1.00
     gynhyrchwyd
    0.94
    webElementGuid
    0.93
     disambiguazione
    0.92
    IndentedString
    0.91
    expandindo
    0.89
    Activations Density 0.293%

    No Known Activations