© 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. 6512
    Prev
    Next
    INDEX
    Explanations

    names of academic institutions, authors, and individuals associated with them

    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
     disambiguazione
    -0.82
     '\\;'
    -0.80
     kaarangay
    -0.76
    +#+#
    -0.72
    LookAnd
    -0.71
     wireType
    -0.69
     صوتيه
    -0.69
    adaptiveStyles
    -0.67
    Autoritní
    -0.66
    oredCriteria
    -0.66
    POSITIVE LOGITS
     |
    0.82
    <eos>
    0.77
     has
    0.74
     vs
    0.73
     was
    0.71
     -
    0.71
     provides
    0.69
     is
    0.68
    :
    0.68
     –
    0.65
    Activations Density 2.379%

    No Known Activations