© 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. 28-GEMMASCOPE-RES-16K
    11. 4555
    Prev
    Next
    INDEX
    Explanations

    references to relationships between characters

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

    preceding verbs or questions

    np_acts-logits-general · gemini-2.0-flash

    who claims or provides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.45
     enjoy
    -0.44
     receiving
    -0.43
     Receiving
    -0.40
     recibiendo
    -0.40
    enjoy
    -0.39
     penerima
    -0.38
    Receiving
    -0.38
    receiving
    -0.37
     enjoyed
    -0.37
    POSITIVE LOGITS
    してくれる
    0.57
    gave
    0.56
     teach
    0.56
     TEACH
    0.56
     gave
    0.56
    してくれた
    0.55
    脚注の使い方
    0.54
     remind
    0.54
     provide
    0.54
    教えて
    0.53
    Activations Density 0.590%

    No Known Activations