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. 22-GEMMASCOPE-RES-16K
    6. 7843
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of the significance of relationships and personal connections

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

    "of the"

    np_acts-logits-general · gemini-2.0-flash

    quantities like many or few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.70
     Monfieur
    -0.70
     myſelf
    -0.69
     Jefus
    -0.69
    ércoles
    -0.67
    المكان
    -0.66
     Theſe
    -0.65
     RSSSF
    -0.64
     themſelves
    -0.64
     himſelf
    -0.64
    POSITIVE LOGITS
     many
    0.97
     few
    0.96
    few
    0.82
     those
    0.81
     wenigen
    0.78
     ujednoznacz
    0.74
    Few
    0.72
     several
    0.71
    many
    0.70
     FEW
    0.70
    Activations Density 0.077%

    No Known Activations