Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3147
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to judicial proceedings

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

    Tokens preceding numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    legal or technical references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tym
    -0.29
    cámara
    -0.28
    ablemente
    -0.28
     students
    -0.27
     customers
    -0.26
    randir
    -0.26
    áneamente
    -0.23
     ме
    -0.23
    ph
    -0.23
     play
    -0.23
    POSITIVE LOGITS
    ⤹
    0.81
     Савезне
    0.78
    цездатний
    0.78
    AISSEE
    0.76
     Мексичка
    0.76
    Personendaten
    0.74
    ↹
    0.73
    AutoModerator
    0.73
    ➯
    0.73
    tanleria
    0.71
    Activations Density 2.821%

    No Known Activations