© 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. 1-GEMMASCOPE-RES-16K
    6. 10597
    Prev
    Next
    INDEX
    Explanations

    academic references and discussions related to recursion and neural networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.70
    twimg
    -0.62
    findpost
    -0.61
     Administrativna
    -0.61
    Lähteet
    -0.60
    softc
    -0.60
    fastjson
    -0.60
    djangoproject
    -0.59
    JspWriter
    -0.58
    MigrationBuilder
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.65
     kidney
    0.57
     punch
    0.56
    omány
    0.55
    ses
    0.55
     recursion
    0.54
    Emission
    0.53
    logy
    0.53
    appendChild
    0.52
     Hilde
    0.51
    Activations Density 2.153%

    No Known Activations