© 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 EvalsExportsAPI 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. 14888
    Prev
    Next
    INDEX
    Explanations

    references to organizational or administrative actions and their outcomes

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

    passive voice constructions with "by" indicating the agent performing an action.

    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
     للمعارف
    -0.57
    PerformLayout
    -0.53
     queſta
    -0.53
    CppMethod
    -0.51
    <<"\
    -0.50
    UnitTesting
    -0.50
    TagHelper
    -0.50
     محفوظة
    -0.50
    unknownFields
    -0.50
    esgue
    -0.49
    POSITIVE LOGITS
     by
    0.56
     jointly
    0.52
    newArrayList
    0.36
    joint
    0.34
     conejo
    0.32
    lewati
    0.31
    IndentedString
    0.31
    haikusbot
    0.31
     JOINT
    0.31
     dibujo
    0.30
    Activations Density 0.318%

    No Known Activations