© 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. 30-GEMMASCOPE-RES-16K
    11. 8797
    Prev
    Next
    INDEX
    Explanations

    references to specific projects and their descriptions

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

    "Project" or "project"

    np_acts-logits-general · gemini-2.0-flash

    project ideas, Manager, Summary, authors

    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
     yên
    -0.44
     financieros
    -0.42
    orElse
    -0.38
     defStyleAttr
    -0.38
     antwoord
    -0.37
     verkoop
    -0.37
     financiera
    -0.36
    AxisAlignment
    -0.36
    bruik
    -0.36
     nakalista
    -0.36
    POSITIVE LOGITS
     Project
    1.05
    Project
    0.97
     PROJECT
    0.95
    getProject
    0.89
     project
    0.88
     projec
    0.84
    PROJECT
    0.83
    project
    0.82
    Projekt
    0.81
     Projek
    0.79
    Activations Density 0.144%

    No Known Activations