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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 10469
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing ideal conditions or recommendations for various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.78
    TestingModule
    -0.76
    onAttach
    -0.69
     Audiodateien
    -0.66
    aarrggbb
    -0.63
    UnknownFieldSet
    -0.62
    原始内容存档于
    -0.61
    BeginInit
    -0.61
    MLLoader
    -0.61
    opsida
    -0.59
    POSITIVE LOGITS
     suited
    0.77
     geeignet
    0.73
     ideal
    0.69
     bagus
    0.68
     suitable
    0.68
    suited
    0.67
     good
    0.66
     adaptées
    0.63
     geschikt
    0.63
     cocok
    0.63
    Activations Density 0.212%

    No Known Activations