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. 18-GEMMASCOPE-RES-16K
    6. 1470
    Prev
    Next
    INDEX
    Explanations

    code-related structures or operations

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

    Tokens within square brackets

    np_acts-logits-general · gemini-2.0-flash

    empty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.67
     kasarigan
    -0.52
    Buildable
    -0.51
    ★★★★☆
    -0.51
     sombra
    -0.50
    Vidite
    -0.49
     vedette
    -0.48
     trống
    -0.48
     ménages
    -0.48
    anément
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.74
     Anſ
    0.69
     Houſe
    0.67
    VolleyError
    0.67
    neſs
    0.67
      (
    0.65
    RectangleBorder
    0.65
    存于互联网档案馆
    0.64
      (
    0.63
    MemoryWarning
    0.61
    Activations Density 0.387%

    No Known Activations