© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7846
    Prev
    Next
    INDEX
    Explanations

    positive affirmations or expressions of approval

    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
     which
    -0.38
     respectively
    -0.36
     onderstaande
    -0.34
     available
    -0.33
     continuously
    -0.33
     quelconque
    -0.32
    といけない
    -0.31
     following
    -0.31
     itself
    -0.30
     worin
    -0.30
    POSITIVE LOGITS
    abestanden
    0.71
    ंदीखरीदारी
    0.68
     esternos
    0.68
     job
    0.66
     snippetHide
    0.66
     noDo
    0.65
     idea
    0.64
     choice
    0.63
     <<<<<<<<<<<<<<
    0.63
    windowFixed
    0.63
    Activations Density 0.286%

    No Known Activations