© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 362
    Prev
    Next
    INDEX
    Explanations

    phrases relating to the efficacy of treatments in clinical studies, particularly concerning radiation and immunotherapy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    RT and immunotherapy combinations

    np_acts-logits-general · gemini-2.0-flash

    prior radiotherapy and immunotherapy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icago
    -0.57
    werp
    -0.56
    Ariel
    -0.56
    EndInit
    -0.55
     lockout
    -0.55
    GHIJKLM
    -0.54
     polis
    -0.53
    licone
    -0.53
     Ariel
    -0.53
    ynth
    -0.53
    POSITIVE LOGITS
     tumor
    1.17
     cancer
    1.06
     Tumor
    1.06
     tumour
    0.97
    Tumor
    0.95
     Cancer
    0.95
     Oncology
    0.93
    tumor
    0.91
     Oncol
    0.91
     tumors
    0.91
    Activations Density 1.537%

    No Known Activations