© 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. 20-GEMMASCOPE-RES-16K
    11. 13784
    Prev
    Next
    INDEX
    Explanations

    methods and processes related to operating vehicles and handling technical tasks

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

    following action verbs/gerunds

    np_acts-logits-general · gemini-2.0-flash

    methods and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.52
    audiovisuel
    -0.48
    Bibliograf
    -0.48
    舺
    -0.47
     nakalista
    -0.46
    LabelTagHelper
    -0.44
    WebpackPlugin
    -0.42
    osoba
    -0.40
    TestingModule
    -0.40
    بدو
    -0.38
    POSITIVE LOGITS
     smtplib
    0.58
     onPostExecute
    0.51
    setupUi
    0.48
     vectorielle
    0.47
     testSet
    0.43
     manutenzione
    0.43
     temporales
    0.43
     isInitialized
    0.42
    ыгана
    0.42
     engraçadas
    0.42
    Activations Density 1.142%

    No Known Activations