© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5827
    Prev
    Next
    INDEX
    Explanations

    future conditional phrases and words indicating predictions or requirements

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

    Follows the word "will"

    np_acts-logits-general · gemini-2.0-flash

    will followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BindingSource
    -0.41
    Дереккөздер
    -0.39
     sales
    -0.38
     Toen
    -0.38
    Trama
    -0.38
    ciąg
    -0.38
     pest
    -0.36
     grass
    -0.36
     Doe
    -0.36
     stock
    -0.35
    POSITIVE LOGITS
     will
    0.69
     youll
    0.64
    存于互联网档案馆
    0.62
    tagHelperRunner
    0.60
     soon
    0.56
     zult
    0.55
     saranno
    0.53
    will
    0.52
     terá
    0.52
    きっと
    0.52
    Activations Density 1.056%

    No Known Activations