© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 2744
    Prev
    Next
    INDEX
    Explanations

    non-verbal elements or formatting within the text

    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
    ahalli
    -0.56
    Tazama
    -0.55
     JAXBElement
    -0.55
    écial
    -0.54
    iformis
    -0.49
     PopupWindow
    -0.48
     affine
    -0.47
    िखित
    -0.47
    ấc
    -0.47
     cof
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.87
    ⓘ
    0.65
    Lähteet
    0.63
    MockBean
    0.63
    曖昧さ回避
    0.62
     CreateTagHelper
    0.62
    WithIOException
    0.62
    তথ্যসূত্র
    0.60
    gameserver
    0.59
     ModelExpression
    0.58
    Activations Density 0.413%

    No Known Activations