© 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. 14005
    Prev
    Next
    INDEX
    Explanations

    specific terminology and references related to programming, particularly in the context of libraries and functions

    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
     OFDb
    -0.83
     snippetHide
    -0.81
    ']")
    -0.80
     estekak
    -0.70
    homonymie
    -0.70
    ValueGenerated
    -0.69
    EDEFAULT
    -0.67
    ագրություններ
    -0.66
    RenderAtEndOf
    -0.65
    ьаж
    -0.65
    POSITIVE LOGITS
    ali
    0.75
    ISupport
    0.67
     Heights
    0.66
     lat
    0.65
    alia
    0.62
    ViewGroup
    0.59
     chords
    0.59
     renamed
    0.59
     ali
    0.58
     amin
    0.58
    Activations Density 2.083%

    No Known Activations