© 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. 18-GEMMASCOPE-RES-16K
    11. 7024
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and criticisms related to individuals or groups

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

    Negative sentiment/calling someone weak or a coward

    np_acts-logits-general · gemini-2.0-flash

    cowardly and weak descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شن
    -0.49
     toegang
    -0.48
    arthed
    -0.46
    geführt
    -0.45
     Zusch
    -0.44
    parsedMessage
    -0.44
    jnych
    -0.44
    Kont
    -0.44
     AssemblyVersion
    -0.42
     urgencia
    -0.42
    POSITIVE LOGITS
     cowardice
    1.63
     coward
    1.53
     cowardly
    1.52
     cowards
    1.44
     weak
    1.43
     wim
    1.42
     timid
    1.37
    weak
    1.26
     soft
    1.21
     Weak
    1.21
    Activations Density 0.399%

    No Known Activations