© 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. 35-GEMMASCOPE-RES-16K
    6. 8250
    Prev
    Next
    INDEX
    Explanations

    code-related structures and functions, particularly those focused on validation processes

    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
     дописавши
    -0.49
     sabbia
    -0.42
    elesen
    -0.41
     regioni
    -0.40
    endregion
    -0.40
    abr
    -0.40
     Mortar
    -0.40
    enol
    -0.38
     mortar
    -0.37
    Tho
    -0.37
    POSITIVE LOGITS
     xxxx
    0.48
     protoimpl
    0.47
    protoimpl
    0.46
     wireType
    0.45
     autorytatywna
    0.45
    دانشنامهٔ
    0.44
    tvguidetime
    0.44
    \{\\
    0.44
    iNdEx
    0.44
    canestro
    0.42
    Activations Density 0.603%

    No Known Activations