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. 13-GEMMASCOPE-RES-16K
    6. 5857
    Prev
    Next
    INDEX
    Explanations

    instances of food-related topics and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }>;
    -0.76
    StoreMessageInfo
    -0.76
    ']>;
    -0.73
    AccessorTable
    -0.70
    '];?>
    -0.66
    UnusedPrivate
    -0.65
     चीज़ों
    -0.63
    ")(
    -0.62
    bewerken
    -0.62
    calaure
    -0.61
    POSITIVE LOGITS
     kebakaran
    0.52
     оса
    0.52
     createSprite
    0.49
     gynhyrchwyd
    0.49
    ніципа
    0.49
    <bos>
    0.47
     CreateTagHelper
    0.47
     udah
    0.45
     scheda
    0.44
    Geografía
    0.44
    Activations Density 0.881%

    No Known Activations