© 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. 3-GEMMASCOPE-RES-16K
    11. 7948
    Prev
    Next
    INDEX
    Explanations

    negative adjectives describing bad conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antMatchers
    -0.68
     VBox
    -0.62
     STAND
    -0.59
     Prest
    -0.58
     PLWABN
    -0.58
     zda
    -0.58
     Tait
    -0.57
     Ain
    -0.56
    รับ
    -0.55
    posites
    -0.55
    POSITIVE LOGITS
     terrible
    1.90
     horrible
    1.88
    terrible
    1.74
     awful
    1.73
     Terrible
    1.70
    Terrible
    1.49
     horribly
    1.47
    Horrible
    1.46
     horrendous
    1.45
    awful
    1.44
    Activations Density 0.051%

    No Known Activations