© 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. 9023
    Prev
    Next
    INDEX
    Explanations

    mentions of challenges and obstacles

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

    "challenge"

    np_acts-logits-general · gemini-2.0-flash

    challenge of

    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
     BorderSide
    -0.66
     AssemblyCulture
    -0.55
     Bescheid
    -0.50
    OGND
    -0.48
     Савезне
    -0.48
     nakalista
    -0.48
    帖最后由
    -0.47
    OCCURRED
    -0.46
     Мексичка
    -0.45
     AssemblyVersion
    -0.45
    POSITIVE LOGITS
     Challenge
    1.28
    Challenge
    1.21
     challenge
    1.20
    challenge
    1.20
     CHALLENGE
    1.19
     Chall
    1.12
     challenges
    1.11
     Challenges
    1.09
     challenging
    1.02
     challeng
    1.02
    Activations Density 0.077%

    No Known Activations