© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3083
    Prev
    Next
    INDEX
    Explanations

    chemical terms and structures often related to synthetic methodologies and molecular interactions

    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
     MainAxisSize
    -0.35
    IntoConstraints
    -0.34
     Λ
    -0.34
     Ло
    -0.31
    batasan
    -0.28
    textAppearance
    -0.28
     Լ
    -0.28
     Ли
    -0.27
    mord
    -0.27
     Li
    -0.27
    POSITIVE LOGITS
    led
    0.85
    ls
    0.81
    l
    0.80
    ⅼ
    0.76
    ldata
    0.74
    ln
    0.73
    list
    0.73
    l
    0.72
    la
    0.71
    lable
    0.71
    Activations Density 1.988%

    No Known Activations