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. 24-GEMMASCOPE-RES-16K
    6. 14198
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

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

    Following a mathematical symbol or character

    np_acts-logits-general · gemini-2.0-flash

    Y or y following x, PV, Round

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omock
    -0.59
     AssemblyTitle
    -0.57
    Bioaccumulative
    -0.53
    WebElementEntity
    -0.52
     שוליים
    -0.51
    XmlAccessType
    -0.51
    ClCompile
    -0.50
     AspNetCore
    -0.48
    AtIndexPath
    -0.48
    脚注の使い方
    -0.47
    POSITIVE LOGITS
     Y
    2.48
    Y
    2.28
     y
    2.15
    getY
    1.74
    YS
    1.68
     YC
    1.68
     getY
    1.66
    YC
    1.66
    YD
    1.65
     YE
    1.62
    Activations Density 2.016%

    No Known Activations