© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14592
    Prev
    Next
    INDEX
    Explanations

    references to challenges or difficulties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.44
     createSprite
    -0.40
     Crook
    -0.37
     uParam
    -0.37
     المعيارى
    -0.35
    protoimpl
    -0.35
    HideFlags
    -0.35
    ScopeManager
    -0.34
    :✨
    -0.34
    basicConfig
    -0.34
    POSITIVE LOGITS
     challenge
    3.86
     challenges
    3.45
    challenge
    3.41
    Challenge
    3.31
     Challenge
    3.31
     CHALLENGE
    3.09
    challenges
    3.08
     Challenges
    3.08
     challenged
    3.00
    Challenges
    2.94
    Activations Density 0.802%

    No Known Activations