© 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. 23-GEMMASCOPE-RES-16K
    6. 8670
    Prev
    Next
    INDEX
    Explanations

    components related to database schema definitions and field attributes

    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
    RemoveField
    -0.35
     died
    -0.35
     pilo
    -0.35
     ri
    -0.34
     Pancake
    -0.34
     defStyleAttr
    -0.33
     Seal
    -0.32
     ordained
    -0.32
    cipy
    -0.31
    sneakers
    -0.31
    POSITIVE LOGITS
    HasMaxLength
    0.66
    exitRule
    0.62
     maxLength
    0.61
     mouthful
    0.58
     maximum
    0.58
    MaxLength
    0.56
     length
    0.56
    length
    0.56
    maxlength
    0.56
    WriteAttribute
    0.55
    Activations Density 0.149%

    No Known Activations