© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7057
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions surrounding strategies, methods, and their implications

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

    Ignoring, neglecting, or excluding something

    np_acts-logits-general · gemini-2.0-flash

    excluding or prioritizing over

    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
     recens
    -0.53
     Genu
    -0.52
    haut
    -0.52
    styleType
    -0.49
    expandindo
    -0.48
    InstrumentedTest
    -0.47
     Chwiliwch
    -0.47
     invokingState
    -0.47
     متعلقه
    -0.46
     المؤلف
    -0.45
    POSITIVE LOGITS
     ignoring
    1.41
     ignore
    1.39
     neglecting
    1.38
     forgetting
    1.36
     forget
    1.32
     forgets
    1.31
     ignores
    1.31
     neglect
    1.28
    forget
    1.22
     forgot
    1.17
    Activations Density 0.392%

    No Known Activations