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. 18-GEMMASCOPE-RES-16K
    6. 14345
    Prev
    Next
    INDEX
    Explanations

    opening curly braces in code or structured text

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

    Mathematical or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical terms

    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
     dikem
    -0.53
     sved
    -0.53
    انيف
    -0.53
    ciech
    -0.52
     InputDecoration
    -0.51
     newState
    -0.51
     transfieras
    -0.51
    Chham
    -0.51
     conftest
    -0.51
     newVal
    -0.50
    POSITIVE LOGITS
    __(/*!
    0.63
    IsContent
    0.63
    ajs
    0.62
    "},
    
    0.59
    发表于
    0.56
    ↵
    0.56
    ')")
    0.55
    ')";
    0.55
    })$}
    0.55
    ={({
    0.54
    Activations Density 0.014%

    No Known Activations