© 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. 519
    Prev
    Next
    INDEX
    Explanations

    numbers associated with a significant concept or metric

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

    Code snippets and bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    code statements ending in semicolon

    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
    CppMethod
    -0.86
     propOrder
    -0.79
    ThemeOverlay
    -0.76
    HostException
    -0.74
    tagHelper
    -0.72
    Portail
    -0.72
    AutoScaleMode
    -0.72
    WebServlet
    -0.71
     transférez
    -0.69
    ázaro
    -0.69
    POSITIVE LOGITS
    ↵↵
    0.78
    <eos>
    0.71
    ↵
    0.69
    enumi
    0.60
     словарь
    0.41
     termica
    0.41
     kuten
    0.39
    UNRELATED
    0.38
     russes
    0.38
    Following
    0.38
    Activations Density 0.166%

    No Known Activations