Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 13524
    Prev
    Next
    INDEX
    Explanations

    terms related to improvement and betterment across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشارکت‌کنندگان
    -0.74
    $_['
    -0.68
    InstanceState
    -0.66
     فريبيس
    -0.63
    ($__
    -0.63
    WillAppear
    -0.63
    ManyToMany
    -0.61
    SequentialGroup
    -0.60
    migrationBuilder
    -0.60
     '\\;'
    -0.60
    POSITIVE LOGITS
     quality
    1.15
     better
    1.08
    better
    1.06
    quality
    1.04
     improved
    1.02
     Better
    1.01
     mejor
    0.98
    Better
    0.97
     BETTER
    0.96
    improved
    0.94
    Activations Density 0.477%

    No Known Activations