© 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. 21-GEMMASCOPE-RES-16K
    6. 10854
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical expressions and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.65
     ainfi
    -0.64
    setVerticalGroup
    -0.57
     pleaſure
    -0.56
    ſelves
    -0.55
    GEBURTSDATUM
    -0.52
    jsxFileName
    -0.51
     ſch
    -0.50
     protoimpl
    -0.49
     perſon
    -0.49
    POSITIVE LOGITS
     sedan
    0.39
    labus
    0.39
     Hotels
    0.38
     TestBed
    0.36
     Coaster
    0.36
     ActiveRecord
    0.35
    umbre
    0.35
    يكب
    0.35
     Universities
    0.35
    providedIn
    0.35
    Activations Density 1.496%

    No Known Activations