Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 828
    Prev
    Next
    INDEX
    Explanations

    instances of nested templates or annotations, especially those related to serialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autique
    -0.72
     Normdatei
    -0.72
    DeleteBehavior
    -0.70
     }}</
    -0.70
     المعرف
    -0.69
    }")]
    -0.69
    yship
    -0.68
    IZONT
    -0.66
     Wiktionnaire
    -0.65
    parsedMessage
    -0.65
    POSITIVE LOGITS
    SerializedName
    0.66
    interopRequire
    0.65
    jupiter
    0.60
    AutoSize
    0.60
     Phys
    0.54
    BackColor
    0.54
     useState
    0.54
    useState
    0.54
    Sprintf
    0.52
    Bronnen
    0.51
    Activations Density 0.020%

    No Known Activations