© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28419
    Prev
    Next
    INDEX
    Explanations

    numerical data related to quantities and statistics

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

    years and preceding text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.71
     PeEnEo
    -0.69
    IUrlHelper
    -0.68
    Datuak
    -0.67
    enumi
    -0.66
     Roskov
    -0.66
    enumii
    -0.63
    BASEPATH
    -0.62
    ValueStyle
    -0.58
    findpost
    -0.58
    POSITIVE LOGITS
     كومونز
    0.57
    aronder
    0.56
    viations
    0.53
    PhysRev
    0.53
    zib
    0.52
    geführten
    0.51
    以内
    0.51
     \]
    0.51
     Allgeme
    0.50
    atics
    0.50
    Activations Density 0.122%

    No Known Activations