© 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. 18-GEMMASCOPE-RES-16K
    11. 440
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional detachment and contrasting states of being

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

    Coldness and apathy

    np_acts-logits-general · gemini-2.0-flash

    emotional coldness and detachment

    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
     resourceCulture
    -0.69
     متعلقه
    -0.67
     complètes
    -0.61
    DataAnnotations
    -0.58
    enumii
    -0.58
     complémentaires
    -0.56
     visibilité
    -0.56
    Cuánto
    -0.54
    Parcelize
    -0.54
     ilegal
    -0.53
    POSITIVE LOGITS
     indifference
    1.34
     indifferent
    1.33
     cold
    1.14
     coldly
    1.13
     nonchal
    1.10
     apathy
    1.06
     indifer
    1.06
     coldness
    1.04
     indiffer
    1.03
    cold
    1.03
    Activations Density 0.282%

    No Known Activations