© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1372
    Prev
    Next
    INDEX
    Explanations

    experiences related to negative or unpleasant emotions

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

    terms related to negative personal experiences or encounters

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

    personal experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.57
    styleType
    -0.52
     adelant
    -0.52
    RectangleBorder
    -0.51
    wts
    -0.50
    ConstraintMaker
    -0.48
     InputDecoration
    -0.47
    onAttach
    -0.47
     avancer
    -0.47
    href
    -0.47
    POSITIVE LOGITS
     experience
    2.63
     experiences
    2.46
    experience
    2.31
     Experience
    2.25
    Experience
    2.24
     Experiences
    2.19
     EXPERIENCE
    2.17
    experiences
    2.14
     expérience
    2.07
     pengalaman
    1.91
    Activations Density 0.151%

    No Known Activations