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. 20-GEMMASCOPE-RES-16K
    6. 5470
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal identification and circumstances surrounding individuals

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

    Japanese text fragments

    np_acts-logits-general · gemini-2.0-flash

    state of not having

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PYX
    -0.60
    DataSetChanged
    -0.56
    Française
    -0.52
    曖昧さ回避
    -0.52
    ьаж
    -0.51
     getItemCount
    -0.51
    ruptedException
    -0.51
     tartalomajánló
    -0.50
    moduleId
    -0.50
     '\\;'
    -0.49
    POSITIVE LOGITS
    로
    0.60
    ברס
    0.54
    BufferException
    0.54
    psack
    0.53
     olarak
    0.52
    にして
    0.50
    více
    0.49
    さで
    0.49
    BagConstraints
    0.47
    ########.
    0.47
    Activations Density 0.065%

    No Known Activations