© 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. 24-GEMMASCOPE-RES-16K
    11. 8703
    Prev
    Next
    INDEX
    Explanations

    issues related to software errors and installation problems

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

    Follows a description of failed attempts

    np_acts-logits-general · gemini-2.0-flash

    tried but failed

    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
    AddTagHelper
    -0.65
     يتيمه
    -0.64
    bootstrapcdn
    -0.62
     queſta
    -0.59
     Normdatei
    -0.57
     arşivlendi
    -0.54
    orianCalendar
    -0.54
    ChildScrollView
    -0.53
    AddHtmlAttribute
    -0.53
    migrationBuilder
    -0.53
    POSITIVE LOGITS
     either
    0.49
     flat
    0.42
     Either
    0.41
     refuses
    0.40
     refused
    0.39
    iar
    0.39
    either
    0.38
    Z
    0.37
    df
    0.37
    omer
    0.36
    Activations Density 0.489%

    No Known Activations