© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3286
    Prev
    Next
    INDEX
    Explanations

    references to obstacles and challenges in various contexts

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

    phrases where "out of the way" or similar expressions describe something being removed, displaced, or no longer obstructing a path.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     følge
    -0.32
    nalités
    -0.30
    CSC
    -0.29
    »
    -0.29
     rejoindre
    -0.28
     chrétien
    -0.27
    matis
    -0.27
    cdef
    -0.27
    BAC
    -0.26
     CSC
    -0.26
    POSITIVE LOGITS
     path
    1.49
     paths
    1.37
     Path
    1.25
     Paths
    1.21
     PATH
    1.20
     pathway
    1.18
    path
    1.16
    PATH
    1.15
     getPath
    1.12
    Path
    1.11
    Activations Density 0.144%

    No Known Activations