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

    Neuronpedia

    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. 9030
    Prev
    Next
    INDEX
    Explanations

    monetary values or measurements expressed in a structured format

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

    "per [time period]"

    np_acts-logits-general · gemini-2.0-flash

    per unit of time or quantity

    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
     Toh
    -0.43
    стви
    -0.42
    hodné
    -0.41
    FDRE
    -0.41
    اتی
    -0.40
     pris
    -0.39
    中の
    -0.38
    りで
    -0.36
     Besch
    -0.36
    록
    -0.36
    POSITIVE LOGITS
    IUrlHelper
    1.09
     annum
    1.05
     day
    0.92
     month
    0.86
     hour
    0.84
    AddTagHelper
    0.79
     متعلقه
    0.79
     week
    0.79
    UIControlState
    0.78
    TargetException
    0.78
    Activations Density 0.192%

    No Known Activations