© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 596
    Prev
    Next
    INDEX
    Explanations

    references to guardians and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    guardian and specific follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.65
    ſelves
    -0.60
     Efq
    -0.60
     bomb
    -0.59
    addPreferredGap
    -0.56
    hésite
    -0.54
     leaſt
    -0.54
     Eſ
    -0.53
     onPostExecute
    -0.52
    enumi
    -0.51
    POSITIVE LOGITS
     Guardian
    0.84
     guardian
    0.83
    Guardian
    0.82
     guardians
    0.72
    ardians
    0.72
     Guardians
    0.72
    guardian
    0.70
    Guardians
    0.68
     guardi
    0.58
    theguardian
    0.55
    Activations Density 0.011%

    No Known Activations