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. 16-GEMMASCOPE-RES-16K
    6. 5058
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly those referring to individuals or groups

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

    Third-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.63
     pomo
    -0.53
    taken
    -0.45
    est
    -0.45
     pras
    -0.45
     ordering
    -0.44
    реш
    -0.44
    anc
    -0.43
    Verde
    -0.42
    řeb
    -0.42
    POSITIVE LOGITS
     can
    0.98
     never
    0.96
     had
    0.95
     would
    0.94
     have
    0.91
     always
    0.90
     didn
    0.89
     still
    0.89
    '):
    
    0.88
     could
    0.86
    Activations Density 0.259%

    No Known Activations