© 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. 27-GEMMASCOPE-RES-16K
    6. 10387
    Prev
    Next
    INDEX
    Explanations

    terms related to projects, legal proceedings, or business operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suppression
    -0.38
     dig
    -0.38
    QUADS
    -0.38
     sup
    -0.36
     register
    -0.35
    change
    -0.35
     suppressed
    -0.35
    supp
    -0.35
    変化
    -0.34
    alternate
    -0.34
    POSITIVE LOGITS
     altogether
    0.90
     completely
    0.88
     kokona
    0.81
     entirely
    0.76
    Completely
    0.74
     Completely
    0.73
    completely
    0.72
    новниш
    0.68
     totally
    0.65
     навсегда
    0.65
    Activations Density 0.608%

    No Known Activations