© 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. 23-GEMMASCOPE-RES-16K
    6. 9646
    Prev
    Next
    INDEX
    Explanations

    keywords related to variable declarations and access modifiers in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulemon
    -0.74
    𝕌
    -0.74
     InputDecoration
    -0.69
     myſelf
    -0.68
    terscotch
    -0.68
     ſind
    -0.65
    ſtanding
    -0.65
    olum
    -0.65
     pleaſure
    -0.65
    Edison
    -0.65
    POSITIVE LOGITS
    private
    1.01
     private
    0.81
     PRIVATE
    0.79
     Private
    0.75
    Private
    0.71
     privada
    0.70
     privaten
    0.68
    PRIVATE
    0.66
     privado
    0.66
     privadas
    0.65
    Activations Density 0.106%

    No Known Activations