© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15558
    Prev
    Next
    INDEX
    Explanations

    negative emotional responses and attitudes towards individuals and policies

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

    words describing negative attitudes or hostility towards people or groups.

    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
    tagHelper
    -0.38
    SOP
    -0.36
    CGRectMake
    -0.34
    illem
    -0.34
    RotationOrder
    -0.32
     bombilla
    -0.31
     AssemblyCompany
    -0.31
     rama
    -0.30
    paddingVertical
    -0.30
    Choice
    -0.30
    POSITIVE LOGITS
     towards
    2.44
     toward
    2.41
    towards
    2.20
    toward
    2.14
     Toward
    2.00
     Towards
    2.00
    Towards
    1.93
    Toward
    1.93
     hacia
    1.70
     envers
    1.66
    Activations Density 0.443%

    No Known Activations