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. 4579
    Prev
    Next
    INDEX
    Explanations

    terms related to defensive actions in sports, particularly interceptions and sacks

    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
     Koz
    -0.44
     raí
    -0.43
     envoie
    -0.43
     Leg
    -0.42
    Sending
    -0.42
     зо
    -0.42
     poveznice
    -0.41
     envoyer
    -0.40
     plagues
    -0.40
     Sending
    -0.40
    POSITIVE LOGITS
     confiscated
    0.87
    rungsseite
    0.80
     Biôgrafia
    0.77
    expandindo
    0.76
    ])));
    0.76
     confis
    0.73
    horabuena
    0.70
     mergeFrom
    0.69
    例句
    0.69
     Pingback
    0.67
    Activations Density 0.184%

    No Known Activations