© 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. 6907
    Prev
    Next
    INDEX
    Explanations

    references to digital platforms and their contents, particularly in the context of software and information access

    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
     this
    -0.59
     those
    -0.46
     therein
    -0.44
     such
    -0.42
     daarvoor
    -0.41
     daarbij
    -0.40
    その
    -0.40
    นั้น
    -0.39
     thereof
    -0.39
     это
    -0.38
    POSITIVE LOGITS
    particular
    0.65
    alone
    0.62
     alone
    0.62
     ALONE
    0.62
     particular
    0.60
     particulier
    0.60
     PARTICULAR
    0.59
    PARTIC
    0.58
     <<<<<<<<<<<<<<
    0.56
     particolare
    0.55
    Activations Density 0.652%

    No Known Activations