© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 3598
    Prev
    Next
    INDEX
    Explanations

    technical terms related to folders and content management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, tags, or group related tokens

    np_acts-logits-general · gemini-2.0-flash

    operation preparer/responder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLD
    -0.79
    SourceChecksum
    -0.77
     CreateTagHelper
    -0.72
    featureID
    -0.70
    ")));
    -0.64
    oredCriteria
    -0.63
     autorytatywna
    -0.63
     nakalista
    -0.62
    mtliche
    -0.62
    Jeografia
    -0.62
    POSITIVE LOGITS
    的能力
    0.56
    Hochspringen
    0.55
    bufio
    0.48
     auprès
    0.48
     by
    0.47
     via
    0.46
     remotely
    0.46
    cmd
    0.45
     помощью
    0.45
     using
    0.45
    Activations Density 0.256%

    No Known Activations