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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 15174
    Prev
    Next
    INDEX
    Explanations

    terms related to interfaces and their implementation in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حوالہ
    -0.53
    andon
    -0.44
     em
    -0.42
    uft
    -0.40
    ("~/
    -0.39
    setContentView
    -0.39
    zelf
    -0.38
     treo
    -0.37
     Trust
    -0.36
     nas
    -0.36
    POSITIVE LOGITS
     interface
    1.43
     interfaces
    1.29
    interfaces
    1.25
    interface
    1.25
    IInterface
    1.20
     Interface
    1.17
     Interfaces
    1.12
    Interface
    1.11
     INTERFACE
    1.08
    接口
    1.02
    Activations Density 0.169%

    No Known Activations