© 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. 3001
    Prev
    Next
    INDEX
    Explanations

    code related to file validation and extensions

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

    File extensions or suffixes

    np_acts-logits-general · gemini-2.0-flash

    file extensions

    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
     سكانية
    -0.57
     mergeFrom
    -0.55
    OGND
    -0.53
    ecraft
    -0.51
     '/';
    -0.50
    RunAsync
    -0.50
    Viitteet
    -0.49
    ();)
    -0.48
    BagLayout
    -0.47
    rafo
    -0.47
    POSITIVE LOGITS
     extension
    1.61
     extensions
    1.48
    extension
    1.45
     Extension
    1.39
    Extension
    1.38
    EXTENSION
    1.29
     Extensions
    1.29
     extensión
    1.28
     EXTENSION
    1.26
    extensions
    1.17
    Activations Density 0.211%

    No Known Activations