© 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. 1-GEMMASCOPE-RES-16K
    6. 9147
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming language elements related to development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.64
     faſt
    -0.61
     Sin
    -0.61
    uesday
    -0.60
    DAOImpl
    -0.59
    Пря
    -0.58
     ſte
    -0.56
     δὲ
    -0.55
    __*/
    -0.55
    Portale
    -0.55
    POSITIVE LOGITS
    ç
    0.62
    transQ
    0.57
    WriteLiteral
    0.56
     AppDelegate
    0.56
    InstanceState
    0.53
    Démographie
    0.53
    Flesh
    0.51
     cop
    0.51
    Jag
    0.51
    CppCodeGen
    0.49
    Activations Density 1.784%

    No Known Activations