© 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 EvalsExportsAPI 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. 15236
    Prev
    Next
    INDEX
    Explanations

    nuanced expressions describing methods, conditions, or perspectives

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

    "In such a [word] that"

    np_acts-logits-general · gemini-2.0-flash

    manner or reason

    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
     EconPapers
    -0.76
     disambiguazione
    -0.72
     HasFactory
    -0.71
    ẢN
    -0.66
     Saltar
    -0.63
     Pingback
    -0.61
    \{\\
    -0.60
    AppCompat
    -0.60
    ủi
    -0.58
     proprement
    -0.57
    POSITIVE LOGITS
     imaginable
    0.64
     tertentu
    0.57
     FetchType
    0.55
     whatsoever
    0.55
    pecified
    0.53
    mangle
    0.52
     determined
    0.52
    UnusedPrivate
    0.51
    limia
    0.49
     manner
    0.49
    Activations Density 0.554%

    No Known Activations