© 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. 6763
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures and conditions of adequacy or inadequacy

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

    "too" or its synonyms in other languages

    np_acts-logits-general · gemini-2.0-flash

    too much

    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
    horabuena
    -0.61
    ]--;
    -0.61
    存于互联网档案馆
    -0.55
    ésultat
    -0.55
    balleur
    -0.55
     parallelogram
    -0.54
    sendStatus
    -0.54
    SaveVideo
    -0.54
    leyball
    -0.53
     retrouve
    -0.52
    POSITIVE LOGITS
     too
    2.18
    Too
    1.98
    too
    1.97
     Too
    1.93
     TOO
    1.72
     слишком
    1.66
     troppo
    1.62
     terlalu
    1.61
     zbyt
    1.51
     demasiado
    1.51
    Activations Density 0.547%

    No Known Activations