© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10085
    Prev
    Next
    INDEX
    Explanations

    phrases expressing emotional or financial distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mack
    -0.49
    <0x88>
    -0.48
     tien
    -0.48
    ensk
    -0.48
     lima
    -0.48
     engender
    -0.47
     afield
    -0.47
    TouchEvent
    -0.46
    Thunk
    -0.46
    permum
    -0.46
    POSITIVE LOGITS
     AssemblyProduct
    0.74
    JspWriter
    0.69
     tfsi
    0.69
    ']):
    0.68
    "]);
    
    0.67
     مشين
    0.65
     defaultstate
    0.64
    "});
    0.63
     busy
    0.63
    aryen
    0.63
    Activations Density 0.205%

    No Known Activations