© 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. 20-GEMMASCOPE-RES-16K
    11. 5496
    Prev
    Next
    INDEX
    Explanations

    relationships between cultural elements and their psychological impacts

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

    Academic surveys and studies

    np_acts-logits-general · gemini-2.0-flash

    academic survey topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ">//
    -0.47
    ziesz
    -0.47
    ريقيا
    -0.46
    opti
    -0.46
    TabStop
    -0.45
    }],
    -0.44
    })()
    -0.42
    ṳ
    -0.40
    ⁢
    -0.40
     fertiliser
    -0.39
    POSITIVE LOGITS
    URLException
    0.88
     resourceCulture
    0.87
    fahan
    0.75
     تضيفلها
    0.72
    SharedDtor
    0.72
     مرئيه
    0.71
     Iranian
    0.71
    HostException
    0.69
     tartalomajánló
    0.69
    mehr
    0.68
    Activations Density 0.179%

    No Known Activations