© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7368
    Prev
    Next
    INDEX
    Explanations

    references to financial audits and their implications on reporting accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    Autoritní
    -0.51
    🔕
    -0.47
     fufficient
    -0.40
    ="#"><
    -0.40
    Derbyniad
    -0.38
    wip
    -0.37
    專
    -0.37
    Tracce
    -0.37
     dokun
    -0.36
     skú
    -0.36
    POSITIVE LOGITS
     biased
    0.68
     bias
    0.64
     AspNetCore
    0.60
     Bias
    0.56
     biases
    0.55
     distortion
    0.55
    bias
    0.55
    EDEFAULT
    0.54
     accurate
    0.54
     BoxFit
    0.53
    Activations Density 0.773%

    No Known Activations