Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1048
    Prev
    Next
    INDEX
    Explanations

    contexts involving authority and penal systems

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

    an assignment or dispatch

    np_acts-logits-general · gemini-2.0-flash

    actions of assignment or release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     protoimpl
    -0.59
    AndEndTag
    -0.56
     فريبيس
    -0.52
    expandindo
    -0.52
    rungsseite
    -0.52
    riwal
    -0.51
    Хьажоргаш
    -0.51
    
    -0.47
    KURZBESCHREIBUNG
    -0.46
     utafitiHapana
    -0.46
    POSITIVE LOGITS
    setopt
    0.46
     tasked
    0.39
     released
    0.37
    AsUp
    0.36
     Assign
    0.35
     mission
    0.34
     charged
    0.34
     assign
    0.34
     lanz
    0.34
    release
    0.34
    Activations Density 0.371%

    No Known Activations