© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12479
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to technical expertise and proficiency

    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
     présidentielle
    -0.89
    SBATCH
    -0.87
    parsedMessage
    -0.86
    Havolalar
    -0.79
     Resolver
    -0.77
     ImGui
    -0.77
     JSP
    -0.76
     Efq
    -0.75
    MessageTagHelper
    -0.74
     мәкалә
    -0.73
    POSITIVE LOGITS
     techniques
    0.93
     technique
    0.90
    TECH
    0.85
     Tech
    0.82
    Tech
    0.79
     TECH
    0.77
    nicos
    0.77
    ities
    0.77
    TECHNICAL
    0.77
    tech
    0.75
    Activations Density 0.033%

    No Known Activations