© 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. 24-GEMMASCOPE-RES-16K
    11. 6896
    Prev
    Next
    INDEX
    Explanations

    references to different modules and their configurations in code

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

    "module"

    np_acts-logits-general · gemini-2.0-flash

    module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goodrich
    -0.46
     voici
    -0.42
     najleps
    -0.41
    EDEFAULT
    -0.40
    s
    -0.40
    ñor
    -0.39
    TheReal
    -0.38
    printStackTrace
    -0.37
    ValueStyle
    -0.37
     izquier
    -0.36
    POSITIVE LOGITS
     Module
    1.09
     Modules
    1.05
    Module
    1.02
     module
    1.02
     MODULE
    0.98
     modules
    0.94
    odule
    0.92
    Modules
    0.91
    module
    0.88
     Modul
    0.87
    Activations Density 0.138%

    No Known Activations