© 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. 4312
    Prev
    Next
    INDEX
    Explanations

    references to channels in various contexts

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

    "channel" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    channel number

    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
    catch
    -0.62
     catch
    -0.61
    herzog
    -0.60
     catching
    -0.59
    Ma
    -0.57
     StatelessWidget
    -0.56
    는
    -0.55
     Ma
    -0.52
    oma
    -0.50
    making
    -0.49
    POSITIVE LOGITS
     channels
    1.41
    Channels
    1.38
     Channels
    1.35
     channel
    1.27
     Channel
    1.24
     CHANNEL
    1.23
    channels
    1.22
    CHANNEL
    1.18
     chanel
    1.16
     channe
    1.15
    Activations Density 0.154%

    No Known Activations