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. 2-GEMMASCOPE-RES-16K
    6. 1135
    Prev
    Next
    INDEX
    Explanations

    terms related to probability, pluralization, and licensing in software contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -0.63
     المعيارى
    -0.63
     للاسماء
    -0.61
    <?
    -0.59
    reactstrap
    -0.58
    WebElementEntity
    -0.58
    ThroughAttribute
    -0.57
    oneofs
    -0.56
    AndroidJUnit
    -0.56
    culously
    -0.56
    POSITIVE LOGITS
     pl
    1.34
    pl
    1.30
    PL
    1.14
     Pl
    1.12
     PL
    1.05
    Pl
    1.04
     Plu
    0.83
     pla
    0.76
    Plu
    0.70
    pla
    0.70
    Activations Density 2.892%

    No Known Activations