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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4311
    Prev
    Next
    INDEX
    Explanations

    types of discontent or dissatisfaction expressed in relation to changes or outcomes

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

    Token followed by "Ma" or "MA"

    np_acts-logits-general · gemini-2.0-flash

    Ma, Mac, MAC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    MOS
    -0.57
     cfs
    -0.55
    min
    -0.52
    mos
    -0.49
     SLS
    -0.48
    мі
    -0.47
    ftagPool
    -0.47
    mut
    -0.46
    MUT
    -0.46
    MenuItem
    -0.46
    POSITIVE LOGITS
     Ma
    2.64
     ma
    2.56
    Ma
    2.54
     MA
    2.33
    ma
    2.27
    MA
    2.15
    Mac
    1.72
     MAC
    1.69
     Mac
    1.68
    MAC
    1.64
    Activations Density 0.428%

    No Known Activations