© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6797
    Prev
    Next
    INDEX
    Explanations

    Angular component declarations and imports

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

    Angular code and components

    np_acts-logits-general · gemini-2.0-flash

    Angular components, modules, directives

    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
    __::
    -0.39
    รา
    -0.39
    #
    -0.38
    AlterField
    -0.37
     Marino
    -0.37
    ｀*)
    -0.37
    /*:
    -0.36
    InvalidProtocol
    -0.36
     Lakeland
    -0.35
    interopRequire
    -0.35
    POSITIVE LOGITS
     NgModule
    0.93
    NgModule
    0.90
     TestBed
    0.86
    ngdoc
    0.76
    providedIn
    0.75
     OnInit
    0.70
     NavController
    0.68
    angular
    0.68
     Angular
    0.67
     CommonModule
    0.66
    Activations Density 0.101%

    No Known Activations