© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4886
    Prev
    Next
    INDEX
    Explanations

    JavaScript and other programming constructs related to tasks, file operations, and string manipulations

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

    Code snippets with string replacements and file paths

    np_acts-logits-general · gemini-2.0-flash

    assigning attributes or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <()>
    -1.10
    RegistryLite
    -0.88
     {}'.
    -0.73
    ())))
    -0.72
    }))
    
    -0.70
    ({})
    -0.69
    })]
    -0.68
     {}".
    -0.68
    {*}
    -0.67
    (_)
    -0.64
    POSITIVE LOGITS
    ("",
    0.95
    ("/",
    0.79
    ('',
    0.75
    ([],
    0.75
    ({},
    0.71
    ('/',
    0.69
    (".",
    0.67
    (_,
    0.64
    BeginContext
    0.62
    ("-",
    0.62
    Activations Density 0.169%

    No Known Activations