© 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. 4-GEMMASCOPE-RES-16K
    6. 11408
    Prev
    Next
    INDEX
    Explanations

    numeric codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.76
     виправивши
    -0.74
    Hentet
    -0.73
    NSNotification
    -0.70
    #
    -0.69
    írus
    -0.64
     suspension
    -0.63
    nologies
    -0.63
     continúas
    -0.62
    ÁRIO
    -0.61
    POSITIVE LOGITS
    :”
    0.58
     Luci
    0.57
    :"
    0.56
     saar
    0.52
     protoimpl
    0.51
     ſen
    0.51
    :'
    0.50
     drago
    0.50
    \:
    0.49
     Dulles
    0.49
    Activations Density 0.395%

    No Known Activations