© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11015
    Prev
    Next
    INDEX
    Explanations

    content related to personal experiences and reflections

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    cause or situation during

    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
    むしろ
    -0.76
     Apalagi
    -0.75
    reszcie
    -0.67
     definitiva
    -0.66
     jopa
    -0.65
     sogar
    -0.65
     zelfs
    -0.65
     definitivo
    -0.64
    何より
    -0.64
    Удачи
    -0.63
    POSITIVE LOGITS
    Naturally
    0.77
     during
    0.76
     Naturally
    0.75
     During
    0.71
    évaluateur
    0.71
    during
    0.70
     prior
    0.68
    During
    0.68
     DURING
    0.65
     due
    0.62
    Activations Density 0.421%

    No Known Activations