© 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. 14128
    Prev
    Next
    INDEX
    Explanations

    phrases related to purpose, objectives, or goals in research and initiatives

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

    "purpose of" or "goal"

    np_acts-logits-general · gemini-2.0-flash

    defining purpose or aim

    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
    Legenda
    -0.50
     manquer
    -0.48
    の手
    -0.48
     कह
    -0.44
     thú
    -0.42
     zuge
    -0.40
     venido
    -0.40
    ior
    -0.40
    vn
    -0.40
    ielded
    -0.40
    POSITIVE LOGITS
    TagMode
    0.89
     aims
    0.82
    帖最后由
    0.80
    httphttps
    0.77
    HasAnnotation
    0.75
    InSection
    0.75
     فريبيس
    0.73
     ensuring
    0.73
     achieving
    0.73
    InjectAttribute
    0.72
    Activations Density 0.239%

    No Known Activations