© 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. 14-GEMMASCOPE-RES-16K
    11. 3258
    Prev
    Next
    INDEX
    Explanations

    terms related to early stages of development or initial phases of processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     derajat
    -0.50
     smaller
    -0.47
     entirely
    -0.46
    }}],
    -0.45
     ex
    -0.44
     small
    -0.44
     verfü
    -0.44
     knowledgeable
    -0.43
    alai
    -0.43
    pec
    -0.43
    POSITIVE LOGITS
    HtmlAttribute
    0.85
     varandra
    0.75
    出版年
    0.72
    InvalidProtocol
    0.72
    Климат
    0.70
    Demografia
    0.70
    AddTagHelper
    0.69
     Dernière
    0.68
    ArgsConstructor
    0.68
     subsequence
    0.66
    Activations Density 0.101%

    No Known Activations