© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3036
    Prev
    Next
    INDEX
    Explanations

    instances of misleading or inaccurate representations and statements in the text

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

    accuracy or misrepresentation

    np_acts-logits-general · gemini-2.0-flash

    accuracy of financial statements

    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
    rungsseite
    -0.48
    🔕
    -0.47
    Autoritní
    -0.45
     OFDb
    -0.42
    Pivot
    -0.40
    專
    -0.40
     ainsi
    -0.39
    reszcie
    -0.39
     küpe
    -0.39
     ağaç
    -0.38
    POSITIVE LOGITS
     accurate
    0.58
    accurate
    0.57
     AspNetCore
    0.56
     inaccurate
    0.55
     exaggerate
    0.54
     distortion
    0.53
     exaggerating
    0.53
    EDEFAULT
    0.52
     truth
    0.52
     Accurate
    0.52
    Activations Density 0.896%

    No Known Activations