© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1741
    Prev
    Next
    INDEX
    Explanations

    references to the name "Victoria" and its variations in different contexts

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

    the word "Victoria" in various contexts (as a proper noun referring to places, people, or titles).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACHUSET
    -0.53
    UnusedPrivate
    -0.48
     outdoors
    -0.45
     Outdoors
    -0.44
     fieldNum
    -0.44
    CppCodeGen
    -0.44
    ftagPool
    -0.43
    NSIndexPath
    -0.43
     pin
    -0.43
     SV
    -0.42
    POSITIVE LOGITS
    Vict
    0.66
     Vict
    0.60
     Vic
    0.47
    VICT
    0.45
    הערות
    0.44
    rawDesc
    0.44
     Victoria
    0.43
     VICT
    0.41
     VIC
    0.40
    Vic
    0.39
    Activations Density 0.117%

    No Known Activations