© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1610
    Prev
    Next
    INDEX
    Explanations

    identifiers and variables used in mathematical expressions

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

    after "a" or "is"

    np_acts-logits-general · gemini-2.0-flash

    is a graded topological vector field

    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
    NSIndexPath
    -0.47
     Carrasco
    -0.44
    GeneratedCode
    -0.42
    trac
    -0.42
     ha
    -0.41
     code
    -0.41
    伝
    -0.40
     resep
    -0.40
    tighet
    -0.40
    jskiej
    -0.40
    POSITIVE LOGITS
    ftagPool
    1.19
     otomatig
    0.89
     onCreateView
    0.88
    出版年
    0.80
    tvguidetime
    0.80
    MigrationBuilder
    0.78
    #+#
    0.77
     ujednoznacz
    0.77
     OFDb
    0.77
     HasFactory
    0.74
    Activations Density 1.681%

    No Known Activations