© 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. 5-GEMMASCOPE-RES-16K
    6. 3594
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to statistical methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.76
    锈钢
    -0.69
     religieuses
    -0.65
     supérieures
    -0.61
    zuf
    -0.56
     understanding
    -0.56
    WithIOException
    -0.55
     uſed
    -0.55
     immobilier
    -0.55
     fufficient
    -0.54
    POSITIVE LOGITS
    enumii
    0.73
     समीक्षाओं
    0.60
    例句
    0.56
    COUVER
    0.48
    ClientSize
    0.48
    】:
    0.47
    çek
    0.46
    abestanden
    0.46
    Cyfeiriadau
    0.45
     مشين
    0.44
    Activations Density 0.571%

    No Known Activations