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. 21-GEMMASCOPE-RES-16K
    6. 12676
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the name "An" and variations of it in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.61
    rawDesc
    -0.59
     المعيارى
    -0.58
    ArrowToggle
    -0.56
    Autoritní
    -0.54
     الرياضيه
    -0.54
     trial
    -0.53
    trial
    -0.52
    stahl
    -0.51
    ffon
    -0.51
    POSITIVE LOGITS
    anadas
    0.47
    KommentareTeilen
    0.44
     AN
    0.44
     kasarigan
    0.43
     alternatives
    0.43
    AsyncResult
    0.42
    Brat
    0.42
    templateUrl
    0.41
    alternatives
    0.41
     capacities
    0.40
    Activations Density 0.069%

    No Known Activations