© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4820
    Prev
    Next
    INDEX
    Explanations

    references to assemblies and their characteristics in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.98
     pears
    -0.96
     تانيه
    -0.94
    OrNil
    -0.88
     BoxFit
    -0.86
     whor
    -0.86
     AssemblyCulture
    -0.86
    fromCharCode
    -0.85
    +:+
    -0.85
     AIAA
    -0.84
    POSITIVE LOGITS
     Assembly
    1.22
     assembly
    1.17
     assemb
    1.10
    assemb
    1.05
    Assembly
    1.04
     ASSEMBLY
    1.01
     assemble
    1.01
     assemblies
    0.99
    EMBLY
    0.96
     assembled
    0.96
    Activations Density 0.114%

    No Known Activations