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. 1-GEMMASCOPE-RES-16K
    6. 14790
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cannot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.70
     kasarigan
    -0.60
    🏻
    -0.57
    $_['
    -0.56
    iel
    -0.55
    er
    -0.55
    cas
    -0.55
    sin
    -0.55
    ora
    -0.54
    ci
    -0.54
    POSITIVE LOGITS
    cannot
    1.17
     cannot
    1.14
     Cannot
    1.01
    Cannot
    1.00
     CANNOT
    0.93
     tidak
    0.86
    xffffffff
    0.84
     nicht
    0.82
    rrggbb
    0.78
     нельзя
    0.77
    Activations Density 0.130%

    No Known Activations