© 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. 31-GEMMASCOPE-RES-16K
    6. 15534
    Prev
    Next
    INDEX
    Explanations

    instances of the word "confront" and its derivatives, indicating themes of confrontation and facing challenges

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

    confrontations or direct face-to-face encounters between opposing parties.

    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
     незавершена
    -0.54
    HasForeignKey
    -0.47
    WriteTagHelper
    -0.45
     OFDb
    -0.45
    يميديا
    -0.40
    hti
    -0.40
     RDS
    -0.40
    esez
    -0.40
    isContained
    -0.40
     cherchés
    -0.40
    POSITIVE LOGITS
     facing
    2.13
     faced
    2.08
     confronted
    1.95
     face
    1.94
     Facing
    1.86
    Facing
    1.80
    facing
    1.77
     confronting
    1.77
    face
    1.68
     Faced
    1.65
    Activations Density 0.213%

    No Known Activations