© 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. 11911
    Prev
    Next
    INDEX
    Explanations

    names or references related to "Ber" or "Berus," which are common prefixes in names and terms

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

    proper names or surnames, particularly those beginning with "Ber".

    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
     ExecuteAsync
    -0.42
    merksamkeit
    -0.38
    Truth
    -0.36
    Tonight
    -0.35
    RuleContext
    -0.34
    Objetivos
    -0.34
     universal
    -0.34
    Threat
    -0.33
    Sú
    -0.33
    Ligações
    -0.32
    POSITIVE LOGITS
     Ber
    0.66
    Ber
    0.63
    AddTagHelper
    0.58
     BER
    0.57
     kasarigan
    0.51
    bero
    0.50
     Бер
    0.50
     Berber
    0.49
     beret
    0.49
     bershka
    0.48
    Activations Density 0.135%

    No Known Activations