© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5724
    Prev
    Next
    INDEX
    Explanations

    terms associated with injections and injection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     razon
    -0.44
    Leon
    -0.43
     dezelve
    -0.42
    tapan
    -0.42
     Leon
    -0.41
     Schmerz
    -0.41
    Tone
    -0.40
     Utile
    -0.40
    oner
    -0.40
    kijken
    -0.40
    POSITIVE LOGITS
     inject
    1.13
     injected
    1.02
     injection
    0.97
     injecting
    0.96
     Injection
    0.92
    Injection
    0.90
    inject
    0.90
     injections
    0.88
    Inject
    0.86
     Inject
    0.85
    Activations Density 0.139%

    No Known Activations