© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1609
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and documentation

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

    Code or conditions featuring "if"

    np_acts-logits-general · gemini-2.0-flash

    conditions based on if

    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
    __":
    
    -0.72
    __':
    
    -0.68
    __":
    -0.62
    __':
    -0.62
    quio
    -0.53
    Pyx
    -0.52
    ंदीखरीदारी
    -0.52
    ymce
    -0.51
    providedIn
    -0.51
    viewDidLoad
    -0.51
    POSITIVE LOGITS
     if
    3.21
    if
    2.64
     dacă
    2.37
     jika
    2.36
     если
    2.36
     nếu
    2.34
     jeśli
    2.15
     якщо
    2.14
     hvis
    2.14
     If
    2.13
    Activations Density 2.028%

    No Known Activations