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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3975
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causal relationships or transitions

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

    "[something], which in turn..."

    np_acts-logits-general · gemini-2.0-flash

    which in turn

    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
     disambiguazione
    -0.88
     ddelweddau
    -0.69
    RenderAtEndOf
    -0.66
     nakalista
    -0.65
     PhpStorm
    -0.61
    cshtml
    -0.61
    WebElementEntity
    -0.60
    AnchorTagHelper
    -0.57
    éens
    -0.56
    ednesdays
    -0.56
    POSITIVE LOGITS
     wiederum
    1.69
     turn
    1.28
     kolei
    1.13
    turn
    1.09
     igjen
    1.09
     then
    0.97
     consequently
    0.94
     subsequently
    0.89
     vervolgens
    0.85
    Turn
    0.83
    Activations Density 0.310%

    No Known Activations