© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 35-GEMMASCOPE-RES-16K
    11. 13205
    Prev
    Next
    INDEX
    Explanations

    terms related to disproportionate effects or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.56
    VersionUID
    -0.50
    AISSEE
    -0.44
    operatives
    -0.43
    发表于
    -0.43
     Numerade
    -0.43
     AssemblyTitle
    -0.42
     ModelExpression
    -0.42
    ouſ
    -0.41
    ächst
    -0.40
    POSITIVE LOGITS
    acious
    0.61
    ulent
    0.60
    volent
    0.59
    orous
    0.56
    ous
    0.56
    icious
    0.54
    uous
    0.53
    varande
    0.50
    tive
    0.50
    SuppressLint
    0.50
    Activations Density 0.688%

    No Known Activations