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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 9518
    Prev
    Next
    INDEX
    Explanations

    terms related to causing damage or negative impacts

    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
    āra
    -0.51
    CODEC
    -0.50
    '}),
    -0.49
     V
    -0.48
     forms
    -0.46
    /}.
    -0.46
    เงิน
    -0.45
    ILayout
    -0.44
    es
    -0.44
     îna
    -0.42
    POSITIVE LOGITS
     spoiling
    1.41
     spoil
    1.33
     ruining
    1.32
     spoiled
    1.27
     ruined
    1.25
     ruin
    1.25
     spoilt
    1.22
     Ruin
    1.13
     spoils
    1.12
    GEBURTSDATUM
    1.10
    Activations Density 0.160%

    No Known Activations