© 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. 15492
    Prev
    Next
    INDEX
    Explanations

    numeric references related to legal or regulatory sections

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

    legal statute and code citations with section numbers.

    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
    躇
    -0.51
     Normdatei
    -0.51
    ()")
    -0.48
     Learners
    -0.45
    =$?
    -0.45
    /**
    -0.44
     للمعارف
    -0.44
    पया
    -0.42
     Lead
    -0.42
    ))}
    -0.42
    POSITIVE LOGITS
    miyorum
    0.40
    MSRP
    0.38
     Administrativna
    0.36
    CloseOperation
    0.36
     comigo
    0.35
     terciopelo
    0.35
    RegisterType
    0.35
    eseorang
    0.35
    unif
    0.35
     Chbosky
    0.34
    Activations Density 0.342%

    No Known Activations