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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 579
    Prev
    Next
    INDEX
    Explanations

    terms related to "derivatives" or words containing "der."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.50
     Preferencias
    -0.44
     ब्रेकडाउन
    -0.43
     Space
    -0.39
    Vendredi
    -0.39
    spedes
    -0.39
    Портали
    -0.39
    UserScript
    -0.39
     XCTest
    -0.39
    ContentAsync
    -0.38
    POSITIVE LOGITS
     Der
    0.77
     DER
    0.66
     der
    0.66
    Der
    0.65
     dere
    0.56
    Dere
    0.54
     Dere
    0.54
     dermat
    0.52
    dere
    0.52
     derma
    0.51
    Activations Density 0.162%

    No Known Activations