© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    elements related to recommendations and positive attributes of various products or experiences

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

    Adjectives describing something favorable

    np_acts-logits-general · gemini-2.0-flash

    positive quality descriptors

    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
     doInBackground
    -0.62
    RenderAtEndOf
    -0.53
     linkovi
    -0.50
    まさか
    -0.48
     angekommen
    -0.48
     Clearly
    -0.47
    Clearly
    -0.47
    yecto
    -0.45
    trui
    -0.44
    AddHtmlAttribute
    -0.44
    POSITIVE LOGITS
     good
    1.25
    good
    1.13
     excellent
    1.05
    excellent
    0.97
     okay
    0.91
     ok
    0.90
     great
    0.90
     preferred
    0.88
     decent
    0.87
     preferable
    0.86
    Activations Density 0.193%

    No Known Activations