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. 7-GEMMASCOPE-RES-16K
    6. 14386
    Prev
    Next
    INDEX
    Explanations

    phrases related to weather and reflections on time's impact on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.68
     Réalisation
    -0.66
    Einzelnachweise
    -0.64
    InitVars
    -0.64
    WarningLevel
    -0.63
    PreferredItem
    -0.60
    ieteur
    -0.59
     externes
    -0.58
     degradability
    -0.56
    Literatur
    -0.56
    POSITIVE LOGITS
     eventful
    0.86
    kwür
    0.57
     nights
    0.55
     stressful
    0.55
     periods
    0.55
     tumultuous
    0.53
     busy
    0.53
     rough
    0.53
    تقاوى
    0.53
     filled
    0.53
    Activations Density 0.207%

    No Known Activations