© 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. 9-GEMMASCOPE-RES-16K
    11. 9168
    Prev
    Next
    INDEX
    Explanations

    descriptions of processes and experiments in a scientific context

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

    descriptions of experimental procedures or methodologies, particularly when actions were performed or carried out.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectMocks
    -0.34
     poly
    -0.29
    мое
    -0.26
     Spez
    -0.26
     Poly
    -0.26
    cmath
    -0.26
    poly
    -0.26
     cop
    -0.26
    dataclass
    -0.26
    moveToFirst
    -0.26
    POSITIVE LOGITS
    الحياه
    0.68
     يتيمه
    0.67
     Meksiku
    0.66
    
    0.66
     autorytatywna
    0.64
     MainAxisSize
    0.57
    arrings
    0.56
    erweise
    0.56
    jsonwebtoken
    0.56
     المعيارى
    0.56
    Activations Density 1.784%

    No Known Activations