© 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. 1-GEMMASCOPE-RES-16K
    6. 14137
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to entities and categories, particularly in contexts involving records or identifiers

    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
    łada
    -0.68
    lessly
    -0.60
    وأضاف
    -0.52
    ำ
    -0.52
    ulence
    -0.52
    ্স
    -0.51
    lés
    -0.49
    ına
    -0.49
     negation
    -0.49
     strictement
    -0.48
    POSITIVE LOGITS
     nakalista
    0.77
     متعلقه
    0.65
     BoxFit
    0.63
    تفصیلات
    0.61
     صوتيه
    0.60
    XMLSchema
    0.60
    LookAnd
    0.58
    XmlAccessorType
    0.58
     Reverso
    0.58
     InputDecoration
    0.57
    Activations Density 3.038%

    No Known Activations