© 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. 265
    Prev
    Next
    INDEX
    Explanations

    instances of monetary transactions or financial discussions

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    items preceded by numerals or specific words

    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
    msgSender
    -0.58
    esterday
    -0.53
    Externé
    -0.50
     resolution
    -0.49
    }$​
    -0.49
    licazione
    -0.48
    NUMX
    -0.48
     jLabel
    -0.48
    …).
    -0.47
    []{"
    -0.47
    POSITIVE LOGITS
    indd
    0.72
    TypedDataSet
    0.65
    Tikang
    0.64
    Datuak
    0.63
     برانيه
    0.61
    wpi
    0.60
     BoxFit
    0.60
     snippetHide
    0.59
    MessageTagHelper
    0.59
    évaluateur
    0.57
    Activations Density 0.274%

    No Known Activations