© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 659
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to future planning and opportunities

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

    Indicates future/further work or investigation

    np_acts-logits-general · gemini-2.0-flash

    future investigation and development

    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
    सन्दर्भ
    -0.43
    getMenuInflater
    -0.40
    postIndex
    -0.39
     instantly
    -0.38
     wrong
    -0.38
    statusText
    -0.38
     Paglinawan
    -0.37
     lul
    -0.36
     tw
    -0.36
    forderung
    -0.36
    POSITIVE LOGITS
     weitere
    0.68
     further
    0.65
     للاسماء
    0.65
     المزيد
    0.61
     kaarangay
    0.59
     weiteren
    0.57
    further
    0.57
    ต่อไป
    0.55
     próximos
    0.55
     kolejne
    0.54
    Activations Density 0.385%

    No Known Activations