© 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. 7618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the introduction or discussion of causes and effects

    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
     Yourself
    -0.55
    Yourself
    -0.50
     yourself
    -0.49
     Myself
    -0.49
    Myself
    -0.47
    myself
    -0.47
     myself
    -0.46
    yourself
    -0.45
     siebie
    -0.44
     используя
    -0.44
    POSITIVE LOGITS
    AccessorTable
    0.68
     createSlice
    0.66
     Numerade
    0.66
    httphttps
    0.65
    ConstraintMaker
    0.60
    rungsseite
    0.59
     havoc
    0.57
    évaluateur
    0.56
     untold
    0.55
     rise
    0.54
    Activations Density 0.863%

    No Known Activations