© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10509
    Prev
    Next
    INDEX
    Explanations

    repetitions of underscores, indicating placeholders or formatting

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

    Underscores

    np_acts-logits-general · gemini-2.0-flash

    IPV6 connection establish trace

    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
    httphttps
    -1.06
     ſind
    -1.03
     queſta
    -0.98
     increí
    -0.97
     faſt
    -0.97
     BoxDecoration
    -0.95
     betweenstory
    -0.94
     iſt
    -0.94
     indígen
    -0.92
     HasFactory
    -0.91
    POSITIVE LOGITS
    _
    1.56
    \_
    1.01
    -
    0.99
    _{
    0.78
    <sub>
    0.69
    }_
    0.65
     _
    0.65
    ‐
    0.65
    _{\
    0.60
    ・
    0.56
    Activations Density 0.553%

    No Known Activations