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. 8101
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "it" and its variations in various contexts

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

    "It" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    "it" followed by 's or verb

    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
     herewith
    -0.56
    mstyle
    -0.55
     hereinafter
    -0.51
     vainly
    -0.51
     proudly
    -0.50
     hereby
    -0.49
     henceforth
    -0.48
     oraz
    -0.47
    ]}"
    -0.46
    :✨
    -0.46
    POSITIVE LOGITS
    NameInMap
    0.87
     StatelessWidget
    0.73
    ########.
    0.71
    abestanden
    0.69
     habido
    0.68
    WithIOException
    0.66
    uxxxx
    0.65
    richTextPanel
    0.65
     sort
    0.62
     Changes
    0.61
    Activations Density 0.135%

    No Known Activations