© 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. 14-GEMMASCOPE-RES-16K
    6. 8751
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and possessive terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.59
     propOrder
    -0.57
    NamedQueries
    -0.48
    AnimationsModule
    -0.47
     Photocase
    -0.46
    Obrázky
    -0.46
    yarnpkg
    -0.45
    InjectAttribute
    -0.45
    uxxxx
    -0.44
    ConstraintMaker
    -0.44
    POSITIVE LOGITS
    AISSEE
    0.43
    
    0.42
    setCellStyle
    0.40
    badah
    0.40
    their
    0.39
     ihrer
    0.38
     τὴν
    0.38
     albicans
    0.38
     elles
    0.38
     internetowa
    0.38
    Activations Density 0.331%

    No Known Activations