© 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. 16-GEMMASCOPE-RES-16K
    11. 1164
    Prev
    Next
    INDEX
    Explanations

    the concept of temporary conditions or actions

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

    "temporarily" or "temporary"

    np_acts-logits-general · gemini-2.0-flash

    temporary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.69
     ModelExpression
    -0.68
    مصادر
    -0.60
    UpInside
    -0.51
    att
    -0.50
    تم
    -0.50
    core
    -0.49
     ATTEND
    -0.48
     Signalez
    -0.48
     kontin
    -0.48
    POSITIVE LOGITS
     temporary
    1.09
     temporarily
    1.07
    Temporary
    1.04
     temporales
    1.00
     Tempor
    0.98
     Temporary
    0.95
    Tempor
    0.95
     tempor
    0.92
    temporary
    0.90
    tempor
    0.90
    Activations Density 0.158%

    No Known Activations