© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 461
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS tags, as well as code structure related to programming

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

    Hexadecimal representations or flags

    np_acts-logits-general · gemini-2.0-flash

    mathematical fractions

    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
    __(/*!
    -0.53
     Rib
    -0.48
    обо
    -0.48
     Desi
    -0.47
     SizedBox
    -0.46
    tica
    -0.46
     Amal
    -0.45
    DataBean
    -0.45
     desi
    -0.44
     }^{(
    -0.44
    POSITIVE LOGITS
    0.99
    0.79
     AssemblyTitle
    0.75
    featureID
    0.70
     gynhyrchwyd
    0.69
    0.66
    EndProject
    0.59
    ThroughAttribute
    0.58
    titleMargin
    0.57
    onomian
    0.55
    Activations Density 0.240%

    No Known Activations