© 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. 16-GEMMASCOPE-RES-16K
    6. 7690
    Prev
    Next
    INDEX
    Explanations

    references to military ranks and titles

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

    Titles (Col, Brig, Captain, Dr.) followed by names

    np_acts-logits-general · gemini-2.0-flash

    rank or title followed by name

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AddTagHelper
    -0.67
     تانيه
    -0.64
    hoeddwyd
    -0.61
    richTextPanel
    -0.60
     <<<<<<<<<<<<<<
    -0.58
     ExecuteAsync
    -0.55
    awtextra
    -0.53
     mostrarán
    -0.53
     باش
    -0.53
    MigrationBuilder
    -0.52
    POSITIVE LOGITS
     myſelf
    0.72
     fhort
    0.71
     himſelf
    0.70
     Emeritus
    0.67
     onely
    0.67
     raiſ
    0.66
     whoſe
    0.66
     Efq
    0.66
    ]--;
    0.66
     ſaid
    0.65
    Activations Density 0.123%

    No Known Activations