© 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. 16-GEMMASCOPE-RES-16K
    11. 4829
    Prev
    Next
    INDEX
    Explanations

    references to software configuration options and settings

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

    Code, settings, or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    configuration options and flags

    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
     sơ
    -0.49
    الحياه
    -0.46
    toContain
    -0.46
    RTEE
    -0.45
    styleUrls
    -0.45
     Auff
    -0.44
    pyx
    -0.43
     createSlice
    -0.43
     recevrez
    -0.43
    cellona
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.84
     option
    0.84
    WriteTagHelper
    0.76
     Option
    0.74
     opção
    0.71
     opción
    0.71
    OGND
    0.70
    option
    0.69
     transfieras
    0.68
     Policy
    0.68
    Activations Density 0.582%

    No Known Activations