Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 869
    Prev
    Next
    INDEX
    Explanations

    passive constructions and references to associations or correlations in data

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

    Following "been" or passive voice

    np_acts-logits-general · gemini-2.0-flash

    has been shown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    MessageOf
    -0.72
    DockStyle
    -0.71
    tableFuture
    -0.68
    ttino
    -0.65
    ^(@)
    -0.65
     iſt
    -0.63
    yntaxException
    -0.63
     purpoſe
    -0.62
    ReusableCell
    -0.60
    WithIOException
    -0.60
    POSITIVE LOGITS
     considered
    1.64
     regarded
    1.39
     deemed
    1.35
    considered
    1.31
     described
    1.27
     Considered
    1.25
     thought
    1.22
     considerado
    1.22
     dianggap
    1.21
     considerada
    1.18
    Activations Density 0.700%

    No Known Activations