© 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. 19-GEMMASCOPE-RES-16K
    6. 11051
    Prev
    Next
    INDEX
    Explanations

    code structure and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.64
    原始内容存档于
    -0.63
    StartCoroutine
    -0.62
    ?";
    -0.61
    tvguidetime
    -0.60
     Efq
    -0.59
    EditorGUILayout
    -0.58
    ChildScrollView
    -0.58
     Профиль
    -0.57
    CodeAttribute
    -0.57
    POSITIVE LOGITS
     my
    0.98
     My
    0.92
    My
    0.87
    my
    0.82
     hello
    0.79
    Demo
    0.77
    foo
    0.77
     test
    0.76
    Test
    0.76
     demo
    0.75
    Activations Density 1.134%

    No Known Activations