© 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. 530
    Prev
    Next
    INDEX
    Explanations

    references to online resources or links

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

    online references and links

    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
     onOptions
    -0.49
     beginnetje
    -0.48
    Sabato
    -0.47
    putExtra
    -0.46
    warts
    -0.44
    強制
    -0.44
    Capítulo
    -0.43
    Spes
    -0.43
    StructEnd
    -0.42
     popo
    -0.42
    POSITIVE LOGITS
    accessed
    0.49
    Pranala
    0.45
     accessed
    0.41
    SourceChecksum
    0.40
    Izvori
    0.40
     Accessed
    0.40
     Wikimedijinoj
    0.39
     Recuperado
    0.39
     consultato
    0.39
     onPostExecute
    0.39
    Activations Density 0.008%

    No Known Activations