© 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. 33-GEMMASCOPE-RES-16K
    11. 7866
    Prev
    Next
    INDEX
    Explanations

    connections and strategies related to overcoming obstacles and vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.46
    profen
    -0.46
     initComponents
    -0.46
     NgModule
    -0.44
    tonsoft
    -0.42
     רע
    -0.41
    řízení
    -0.41
     Apo
    -0.41
    adpleegd
    -0.41
    Apo
    -0.39
    POSITIVE LOGITS
     bypass
    1.80
     circumvent
    1.78
     bypassing
    1.70
     bypassed
    1.64
    bypass
    1.46
     Byp
    1.44
     overcoming
    1.43
     overcome
    1.41
     Bypass
    1.41
     overcomes
    1.40
    Activations Density 0.954%

    No Known Activations