© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2575
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting a consistent belief or value over time

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

    Followed by a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    always + verb

    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
     recently
    -0.83
    esterday
    -0.81
     currently
    -0.80
    recently
    -0.72
     momentan
    -0.70
     newly
    -0.69
     now
    -0.69
     yesterday
    -0.69
     kürzlich
    -0.68
    currently
    -0.68
    POSITIVE LOGITS
    以來
    0.70
    一直
    0.69
    endphp
    0.63
    always
    0.59
    Always
    0.57
    Siempre
    0.57
     Always
    0.56
    siempre
    0.56
     always
    0.55
     hinweg
    0.55
    Activations Density 0.271%

    No Known Activations