© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6754
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure, particularly in contexts involving scripts and code implementation

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

    Code, commands, and file paths

    np_acts-logits-general · gemini-2.0-flash

    academic, legal, and code referencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.59
    sidemargin
    -0.52
    GeneratedValue
    -0.47
    jsxFileName
    -0.47
    SBATCH
    -0.46
     تكبرها
    -0.45
    ↹
    -0.44
    twimg
    -0.42
    unhofer
    -0.42
    clientY
    -0.41
    POSITIVE LOGITS
     dentaire
    0.45
     ujednoznacz
    0.44
     AppCompatTheme
    0.43
    aulted
    0.40
    ighters
    0.40
    存于互联网档案馆
    0.39
    qxd
    0.39
     Italij
    0.39
    sarung
    0.39
     chande
    0.38
    Activations Density 1.157%

    No Known Activations