© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1143
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminologies related to regulation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    醐
    -0.58
    بوابة
    -0.54
     发表于
    -0.52
    withIdentifier
    -0.47
     Good
    -0.44
     Cons
    -0.43
     sk
    -0.43
    icated
    -0.41
     custom
    -0.41
     Q
    -0.41
    POSITIVE LOGITS
     AttributeSet
    0.77
     tartalomajánló
    0.73
     ainfi
    0.69
     ſind
    0.68
    rfloor
    0.63
     auffi
    0.63
     itſelf
    0.61
     aveug
    0.59
     pulito
    0.58
     bezeichneter
    0.58
    Activations Density 1.785%

    No Known Activations