© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7949
    Prev
    Next
    INDEX
    Explanations

    elements related to survival rates and performance metrics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.59
    पया
    -0.58
    migrationBuilder
    -0.43
    quiao
    -0.41
    celotti
    -0.41
     мәкал
    -0.40
    HasForeignKey
    -0.40
    brainer
    -0.38
     оригіналу
    -0.38
    المناصب
    -0.38
    POSITIVE LOGITS
     rate
    1.10
     ratio
    1.09
     intensity
    0.93
     rates
    0.92
    率
    0.89
     levels
    0.88
     ratios
    0.88
     quotient
    0.85
     density
    0.85
     capacity
    0.82
    Activations Density 2.046%

    No Known Activations