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. 22-GEMMASCOPE-RES-16K
    6. 11414
    Prev
    Next
    INDEX
    Explanations

    informal conversational expressions or phrases

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

    after "know"

    np_acts-logits-general · gemini-2.0-flash

    know, grasp, or 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.83
    Hentet
    -0.79
     ſtate
    -0.72
    хьтан
    -0.71
    UnsafeEnabled
    -0.70
    twimg
    -0.69
     fubject
    -0.68
     fevere
    -0.68
     Majefty
    -0.68
     Efq
    -0.68
    POSITIVE LOGITS
    Enllaces
    0.55
     I
    0.51
    ')):
    0.50
    `,`
    0.50
     um
    0.49
     what
    0.49
     uh
    0.48
    ifdef
    0.48
    KommentareTeilen
    0.46
     ehem
    0.46
    Activations Density 0.052%

    No Known Activations