Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4318
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and structures used in document preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.66
     pleaſure
    -0.62
     ſta
    -0.60
    ſelf
    -0.54
     raiſ
    -0.52
     Majefty
    -0.51
     canst
    -0.51
     ſur
    -0.50
     poffible
    -0.50
     poffe
    -0.50
    POSITIVE LOGITS
    usepackage
    0.71
    Declare
    0.52
    newcommand
    0.47
    pagestyle
    0.43
    Pass
    0.42
    Билгалдахарш
    0.42
    setcounter
    0.41
    Define
    0.40
     Declare
    0.39
    title
    0.38
    Activations Density 0.145%

    No Known Activations