© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    patterns of financial or economic data identifiers and references

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

    Mathematical notation or code followed by "s"

    np_acts-logits-general · gemini-2.0-flash

    S followed by s or Science

    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
    rungsseite
    -0.64
    Personensuche
    -0.64
     lccn
    -0.61
    脚注の使い方
    -0.59
     LEYENDO
    -0.58
    ंदीखरीदारी
    -0.53
    NotBlank
    -0.53
    mybatisplus
    -0.52
    NewReader
    -0.52
    
    -0.52
    POSITIVE LOGITS
     S
    0.93
    S
    0.82
     s
    0.74
     س
    0.67
     Science
    0.65
    Science
    0.63
     science
    0.60
    S
    0.60
     South
    0.59
    Social
    0.59
    Activations Density 1.797%

    No Known Activations