© 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. 18-GEMMASCOPE-RES-16K
    6. 2850
    Prev
    Next
    INDEX
    Explanations

    temporal references, particularly specific months and seasons

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

    Months of the year

    np_acts-logits-general · gemini-2.0-flash

    names of months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.75
    IGraphics
    -0.71
     esternos
    -0.68
     CreateTagHelper
    -0.63
     ModelExpression
    -0.61
    contentLoaded
    -0.60
    >`;
    -0.60
    esModule
    -0.59
    ')";
    -0.58
    ValueGeneration
    -0.58
    POSITIVE LOGITS
    February
    0.59
     yyl
    0.57
    March
    0.57
     equinox
    0.56
     меся
    0.56
     måned
    0.56
     umana
    0.54
     urbaine
    0.51
    April
    0.51
     fevere
    0.51
    Activations Density 0.157%

    No Known Activations