© 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. 11048
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to inequalities and integrals

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

    Fractions or ratios

    np_acts-logits-general · gemini-2.0-flash

    numbers and comparisons

    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
     Infórmanos
    -0.68
    KURZBESCHREIBUNG
    -0.59
    IndentedString
    -0.56
    protoimpl
    -0.56
    InitVars
    -0.54
    Cartney
    -0.54
    WriteTagHelper
    -0.52
     gynhyrchwyd
    -0.52
    Véxase
    -0.51
    SourceChecksum
    -0.51
    POSITIVE LOGITS
     <=
    0.72
     ≤
    0.68
    yarnpkg
    0.68
    npmjs
    0.59
    XmlAccessType
    0.58
    ≤
    0.55
    leq
    0.55
    Espèce
    0.54
    URLException
    0.54
    __(/*!
    0.53
    Activations Density 0.630%

    No Known Activations