© 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. 28-GEMMASCOPE-RES-16K
    6. 7075
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their properties in code

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

    Code snippets containing "source" or "node"

    np_acts-logits-general · gemini-2.0-flash

    named, source, and storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.76
     snippetHide
    -0.74
    __':
    
    -0.68
     queſta
    -0.65
    ThroughAttribute
    -0.65
    __":
    
    -0.64
     '\\;'
    -0.64
    Clik
    -0.62
    FormTagHelper
    -0.61
    <unused8>
    -0.60
    POSITIVE LOGITS
    Personendaten
    0.41
    nameof
    0.38
    HasColumnName
    0.38
     bernama
    0.35
     called
    0.34
    便是
    0.32
    PyExc
    0.31
    ('
    0.30
    名为
    0.30
     praça
    0.30
    Activations Density 1.150%

    No Known Activations