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. 7952
    Prev
    Next
    INDEX
    Explanations

    instances of time and frequency indicators within contexts

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

    Prepositions followed by "a" or "one"

    np_acts-logits-general · gemini-2.0-flash

    at a time

    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
     myſelf
    -1.38
     disambiguazione
    -1.33
    contentLoaded
    -1.28
    OGND
    -1.22
     Monfieur
    -1.18
     Theſe
    -1.17
     raiſ
    -1.16
     ainfi
    -1.16
     houſe
    -1.15
     estekak
    -1.14
    POSITIVE LOGITS
     
    0.94
     a
    0.84
     (
    0.76
     an
    0.72
     the
    0.71
     C
    0.70
     B
    0.69
     e
    0.68
     I
    0.68
     Re
    0.67
    Activations Density 1.007%

    No Known Activations