© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 80
    Prev
    Next
    INDEX
    Explanations

    statements and phrases related to reasoning or justification

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

    "reason" and its variations, often followed by "for"

    np_acts-logits-general · gemini-2.0-flash

    reason for

    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
     يتيمه
    -0.94
     AssemblyCompany
    -0.89
    ագրություններ
    -0.88
     Audiodateien
    -0.86
    Datuak
    -0.81
    مقاله
    -0.79
    mybatisplus
    -0.77
     createSlice
    -0.76
     >=",
    -0.76
    Izvori
    -0.75
    POSITIVE LOGITS
     why
    1.29
     reason
    1.09
     reasons
    1.04
    why
    1.00
    Reason
    0.95
     Reason
    0.95
    reasons
    0.95
    reason
    0.91
     REASON
    0.89
     Reasons
    0.88
    Activations Density 0.173%

    No Known Activations