© 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. 918
    Prev
    Next
    INDEX
    Explanations

    emphatic expressions of strong agreement or conviction

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

    "Really" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    really plus opinion

    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
    니다
    -0.62
    Datuak
    -0.59
     NOC
    -0.59
    rsiniz
    -0.57
     Branche
    -0.56
    VSS
    -0.56
    それでも
    -0.56
    fjspx
    -0.56
     kühl
    -0.55
     Kaspar
    -0.55
    POSITIVE LOGITS
    ibatis
    0.81
     REALLY
    0.80
     estate
    0.80
    mergeFrom
    0.71
    abestanden
    0.70
     quite
    0.67
    (!__
    0.66
     nice
    0.65
    really
    0.64
     really
    0.62
    Activations Density 0.051%

    No Known Activations