© 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. 1678
    Prev
    Next
    INDEX
    Explanations

    discussions about personal growth and healing from emotional struggles

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

    the word "self"

    np_acts-logits-general · gemini-2.0-flash

    self pronouns and empowerment

    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
    •harmless_evil_confidant_18

    No Comments

    Negative Logits
    רב
    -0.51
     createState
    -0.49
    asinya
    -0.49
    ecuzione
    -0.47
     Urqu
    -0.47
     Nadel
    -0.46
     nakalista
    -0.46
    WithIOException
    -0.46
     Raceway
    -0.46
    __((
    -0.44
    POSITIVE LOGITS
     self
    0.98
     SELF
    0.93
     Self
    0.92
    Self
    0.86
    SELF
    0.78
    self
    0.71
     empower
    0.69
     Asser
    0.69
     inner
    0.68
     empowering
    0.68
    Activations Density 0.171%

    No Known Activations