© 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. 35-GEMMASCOPE-RES-16K
    11. 12112
    Prev
    Next
    INDEX
    Explanations

    technical words related to analysis and modeling in scientific contexts

    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
    Datuak
    -0.60
     nakalista
    -0.47
    mtrl
    -0.47
    PreferredItem
    -0.47
     seperate
    -0.47
     AttributeSet
    -0.46
    eseorang
    -0.42
    primarily
    -0.42
    ⤹
    -0.42
    المكان
    -0.41
    POSITIVE LOGITS
    Nowadays
    0.73
     viceversa
    0.73
     nowadays
    0.70
     Nowadays
    0.70
     confortable
    0.60
     evidences
    0.59
     potentialities
    0.59
     preliminar
    0.57
     everybody
    0.57
     Anyway
    0.57
    Activations Density 4.035%

    No Known Activations