© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1816
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and terms related to poor quality or undesirable attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.75
    bkz
    -0.66
     محفوظة
    -0.64
    __':
    -0.64
    RectangleBorder
    -0.63
    marginHorizontal
    -0.60
     Theſe
    -0.60
    /*
    -0.60
    rijke
    -0.59
    WireFormatLite
    -0.59
    POSITIVE LOGITS
     bad
    1.10
    Bad
    0.99
     Bad
    0.97
    bad
    0.97
     BAD
    0.87
    BAD
    0.82
    gering
    0.69
     worse
    0.69
    ajoz
    0.67
     badly
    0.63
    Activations Density 0.095%

    No Known Activations