© 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. 3-GEMMASCOPE-RES-16K
    11. 6233
    Prev
    Next
    INDEX
    Explanations

    expressions of affirmation and strong opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.51
     The
    -0.37
    ↵
    -0.37
    The
    -0.32
    ↵↵↵↵↵↵↵
    -0.28
    “
    -0.27
    <eos>
    -0.27
    ↵↵↵↵↵↵↵↵↵
    -0.27
    チール
    -0.26
     Children
    -0.25
    POSITIVE LOGITS
    AddTagHelper
    0.84
    GOTREF
    0.82
     beſte
    0.76
    tagHelperRunner
    0.73
     ſeinen
    0.71
     semelh
    0.70
     dieſem
    0.68
    RemoveField
    0.68
     dieſe
    0.68
    Quite
    0.68
    Activations Density 0.742%

    No Known Activations