© 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. 16-GEMMASCOPE-RES-16K
    11. 4859
    Prev
    Next
    INDEX
    Explanations

    complex sentences with conjunctions and clauses

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

    Sentences preceding transition words

    np_acts-logits-general · gemini-2.0-flash

    consequence indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.80
    Cyfeiriadau
    -0.79
     AssemblyCulture
    -0.72
    Personendaten
    -0.72
     Numerade
    -0.70
    OGND
    -0.69
     Administrativna
    -0.69
     صوتيه
    -0.69
    GEBURTSDATUM
    -0.68
    NewUrlParser
    -0.66
    POSITIVE LOGITS
     therefore
    0.72
     Worse
    0.70
     Поэтому
    0.69
     Therefore
    0.69
    所以在
    0.69
     thus
    0.69
     поэтому
    0.68
     hence
    0.67
    所以
    0.67
    Therefore
    0.66
    Activations Density 0.415%

    No Known Activations