Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4237
    Prev
    Next
    INDEX
    Explanations

    references to parenting and family dynamics

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

    Possessive pronouns followed by family member

    np_acts-logits-general · gemini-2.0-flash

    possessive determiners + child/offspring

    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
    UserScript
    -0.81
     widow
    -0.73
    dafx
    -0.72
    httphttps
    -0.67
     widows
    -0.66
     المعيارى
    -0.65
    enumii
    -0.63
     grandparents
    -0.63
    kháu
    -0.62
     grandfather
    -0.62
    POSITIVE LOGITS
    andExpect
    0.66
     angel
    0.64
     bundle
    0.63
     charges
    0.60
     little
    0.59
     precious
    0.58
     special
    0.55
     charge
    0.55
     fur
    0.54
     Charges
    0.53
    Activations Density 0.094%

    No Known Activations