Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15980
    Prev
    Next
    INDEX
    Explanations

    technical terms related to steam locomotives and their operation

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

    Mention of locomotives or engines

    np_acts-logits-general · gemini-2.0-flash

    locomotive and steam engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.65
    enderror
    -0.49
    IntoConstraints
    -0.48
     PhpStorm
    -0.48
    DockStyle
    -0.48
    <?
    -0.47
     tartalomajánló
    -0.44
     yyr
    -0.43
    EndContext
    -0.43
     vå
    -0.43
    POSITIVE LOGITS
     steam
    1.11
     Steam
    1.02
    Steam
    0.99
     engine
    0.96
    steam
    0.94
     Engine
    0.93
     engines
    0.89
     Engines
    0.82
    Engine
    0.82
     locomotive
    0.80
    Activations Density 0.073%

    No Known Activations