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. 8279
    Prev
    Next
    INDEX
    Explanations

    references to academic qualifications and titles

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

    HTML title tag

    np_acts-logits-general · gemini-2.0-flash

    title

    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
     CreateTagHelper
    -0.67
     ErrIntOverflow
    -0.62
    исленность
    -0.57
     CallOverrides
    -0.54
    CodeDom
    -0.53
     >=",
    -0.53
    AppCompatTheme
    -0.53
     unknownFields
    -0.52
     الرياضيه
    -0.52
     anastom
    -0.51
    POSITIVE LOGITS
     title
    3.41
    title
    3.04
     Title
    2.78
    Title
    2.71
     TITLE
    2.56
     titles
    2.49
    TITLE
    2.45
     título
    2.33
     titel
    2.20
     titolo
    2.07
    Activations Density 0.183%

    No Known Activations