© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2976
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial outcomes and assessments

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

    Comes before "off" after indicating sentiment

    np_acts-logits-general · gemini-2.0-flash

    better off, signed off, ticked off, pays off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.73
     MainAxisSize
    -0.64
    OGND
    -0.62
    InitVars
    -0.59
    NgModule
    -0.57
    تقاوى
    -0.57
    LayoutPanel
    -0.57
    tagHelperRunner
    -0.55
    IsContent
    -0.55
    DrawerToggle
    -0.53
    POSITIVE LOGITS
     off
    4.56
    off
    3.63
     Off
    3.63
    Off
    3.55
     OFF
    3.18
    OFF
    2.88
    offs
    2.61
     offs
    2.60
    オフ
    2.43
     オフ
    1.90
    Activations Density 0.728%

    No Known Activations