© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 463
    Prev
    Next
    INDEX
    Explanations

    instances of logical falsehoods or negations in code

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

    Boolean "false" values

    np_acts-logits-general · gemini-2.0-flash

    false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.71
    bootstrapcdn
    -0.64
    tabular
    -0.61
    ingway
    -0.58
     kasarigan
    -0.56
    KommentareTeilen
    -0.56
    Viking
    -0.55
     snippetHide
    -0.55
    pidou
    -0.54
     سكانية
    -0.53
    POSITIVE LOGITS
     False
    1.15
     false
    1.13
    False
    1.08
    false
    1.07
     FALSE
    0.96
    FALSE
    0.88
     falsa
    0.81
     falsos
    0.79
     fausse
    0.79
     falsas
    0.75
    Activations Density 0.077%

    No Known Activations