© 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. 30-GEMMASCOPE-RES-16K
    11. 13021
    Prev
    Next
    INDEX
    Explanations

    names and details related to historical events and figures

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

    Tokens before "based", "in", "players", "births"

    np_acts-logits-general · gemini-2.0-flash

    category names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.79
    awtextra
    -0.65
     <<<<<<<<<<<<<<
    -0.62
    rungsseite
    -0.57
     Meksiku
    -0.54
     فريبيس
    -0.50
    hoeddwyd
    -0.50
    MigrationBuilder
    -0.49
     OnInit
    -0.49
    Autowired
    -0.46
    POSITIVE LOGITS
     Template
    0.53
    Template
    0.48
     Ground
    0.41
     Progress
    0.40
     prédé
    0.39
     virkelig
    0.39
    œil
    0.38
     template
    0.37
     Gabb
    0.37
     fungerer
    0.37
    Activations Density 1.008%

    No Known Activations