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. 10526
    Prev
    Next
    INDEX
    Explanations

    the word "Ne" and its variations, likely indicating a focus on neural or neurobiological terms

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

    Tokens starting with "Ne" or "ne"

    np_acts-logits-general · gemini-2.0-flash

    words starting with "N"

    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
     onOptions
    -0.62
    CodeAttribute
    -0.59
    ọa
    -0.58
    MemoryWarning
    -0.58
    })*/
    -0.58
     createSprite
    -0.52
     rũ
    -0.52
    TargetException
    -0.52
    existsSync
    -0.52
     Himo
    -0.52
    POSITIVE LOGITS
     Ne
    0.64
    Ne
    0.62
     cherchés
    0.57
     Neff
    0.56
     Neel
    0.53
     Neville
    0.53
     VOUS
    0.51
    Filmografie
    0.49
     pār
    0.49
     Neumann
    0.49
    Activations Density 0.122%

    No Known Activations