© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    references to academic papers, lectures, and discussions in a scholarly context

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

    after specific series-related terms

    np_acts-logits-general · gemini-2.0-flash

    Series, concert, sessions, orthogonal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.39
     OMITTED
    -0.37
     Anhang
    -0.36
    vested
    -0.36
    سایت
    -0.35
    MergeFrom
    -0.34
     padx
    -0.33
    cuál
    -0.33
    LEncoder
    -0.32
    WithMany
    -0.32
    POSITIVE LOGITS
     lectures
    0.55
    providedIn
    0.54
    verwijspagina
    0.53
    fjspx
    0.52
     concerts
    0.52
     lecture
    0.51
    lecture
    0.49
     weekly
    0.49
     concert
    0.49
     webinar
    0.48
    Activations Density 0.493%

    No Known Activations