© 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. 8352
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical outcomes and comparisons

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

    Numbers and symbols in a technical or mathematical context

    np_acts-logits-general · gemini-2.0-flash

    numbers, symbols, and code

    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
     pleaſure
    -0.68
    RTRS
    -0.67
    Boring
    -0.65
     <=",
    -0.65
    resave
    -0.63
    ⎠
    -0.62
    rrggbb
    -0.61
    boring
    -0.61
     Efq
    -0.59
    POSITIVE LOGITS
    MessageTagHelper
    0.53
     Rem
    0.47
     gyhoeddwyd
    0.46
     actionMode
    0.45
     san
    0.45
     dar
    0.42
    یمی
    0.42
    InitStruct
    0.41
     San
    0.41
    taan
    0.41
    Activations Density 0.702%

    No Known Activations