© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8002
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal choices and decision-making

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

    Reflexive pronouns following certain verbs

    np_acts-logits-general · gemini-2.0-flash

    reflexive self-reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itself
    -0.81
    himself
    -0.75
     egna
    -0.73
    herself
    -0.73
     Itself
    -0.68
     suaminya
    -0.67
     nią
    -0.66
     Himself
    -0.64
    she
    -0.64
     InputDecoration
    -0.63
    POSITIVE LOGITS
    #+#
    0.76
     himo
    0.72
     mys
    0.69
    帖最后由
    0.67
     hini
    0.62
     المعيارى
    0.59
     themes
    0.57
    Personensuche
    0.54
     Ones
    0.50
    ondissement
    0.49
    Activations Density 0.074%

    No Known Activations