© 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. 28-GEMMASCOPE-RES-16K
    6. 3919
    Prev
    Next
    INDEX
    Explanations

    references to collective experiences and interactions within groups

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

    Follows "we" and indicates conversation

    np_acts-logits-general · gemini-2.0-flash

    we discussed

    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
     للمعارف
    -0.49
     kasarigan
    -0.43
    karta
    -0.40
    Hostname
    -0.39
     PIT
    -0.38
    zegovina
    -0.36
     competence
    -0.36
     answer
    -0.35
    writeField
    -0.35
     الدولي
    -0.35
    POSITIVE LOGITS
     discussed
    0.62
     ProtoMessage
    0.60
     intptr
    0.56
    Discuss
    0.54
    ślę
    0.53
     Discuss
    0.52
    ölkerung
    0.52
     discussion
    0.51
     discuss
    0.49
     обсу
    0.49
    Activations Density 0.253%

    No Known Activations