© 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. 4085
    Prev
    Next
    INDEX
    Explanations

    database-related annotations and identifiers in code

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

    Code snippets or identifiers

    np_acts-logits-general · gemini-2.0-flash

    unique identifiers

    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
    pushFollow
    -0.72
    MockBean
    -0.68
     nakalista
    -0.66
    SuspendLayout
    -0.66
    matchCondition
    -0.66
    aarrggbb
    -0.65
     урна
    -0.65
     ComVisible
    -0.65
    TestingModule
    -0.64
    avyzd
    -0.64
    POSITIVE LOGITS
     Id
    0.64
     UUID
    0.64
     id
    0.63
    UUID
    0.62
    getId
    0.61
    AutoField
    0.61
     uuid
    0.55
     Guid
    0.54
    Guid
    0.54
    Serializable
    0.52
    Activations Density 0.047%

    No Known Activations