© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9071
    Prev
    Next
    INDEX
    Explanations

    the word "from."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.80
     itſelf
    -0.76
    expandindo
    -0.71
     Majefty
    -0.69
     purpoſe
    -0.68
     Wart
    -0.67
     ་་
    -0.66
    iertas
    -0.65
     Houſe
    -0.65
     thri
    -0.64
    POSITIVE LOGITS
     from
    3.63
     FROM
    3.08
    from
    3.00
     From
    2.82
    From
    2.66
    FROM
    2.65
     från
    2.43
     từ
    2.26
     dari
    2.25
    จาก
    2.20
    Activations Density 0.276%

    No Known Activations