© 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. 31-GEMMASCOPE-RES-16K
    11. 4257
    Prev
    Next
    INDEX
    Explanations

    objects and locations commonly associated with domestic or functional settings

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

    words referring to physical locations or surfaces where people or objects are positioned.

    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
    .*")]
    -0.42
     waarin
    -0.38
    cstdio
    -0.38
    oen
    -0.37
     steckt
    -0.34
    Sug
    -0.33
    itario
    -0.33
    piram
    -0.33
    写在
    -0.33
     Rees
    -0.32
    POSITIVE LOGITS
     waarop
    1.00
    Personendaten
    0.70
    AndEndTag
    0.69
    上的
    0.64
    ChildScrollView
    0.58
     AssemblyCompany
    0.57
    IntoConstraints
    0.54
     typelib
    0.53
    tagext
    0.51
    밌
    0.51
    Activations Density 0.651%

    No Known Activations