© 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. 5-GEMMASCOPE-RES-16K
    11. 15162
    Prev
    Next
    INDEX
    Explanations

    programming languages and related terminology in computer science contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ioutil
    -0.51
    zetek
    -0.46
    makeConstraints
    -0.45
    MENAFN
    -0.41
    Bara
    -0.41
     hefyd
    -0.40
     vedno
    -0.39
    ట
    -0.39
    สำคัญ
    -0.39
    捗
    -0.39
    POSITIVE LOGITS
     للاسماء
    0.85
    featureID
    0.85
    UserScript
    0.77
    ThroughAttribute
    0.72
    ExecuteReader
    0.70
    IUrlHelper
    0.67
    المشاركات
    0.65
     AssemblyTitle
    0.65
    MigrationBuilder
    0.64
     <>",
    0.64
    Activations Density 0.722%

    No Known Activations