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. 8-GEMMASCOPE-RES-16K
    6. 6071
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatments and their effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     standard
    -0.45
    SerializeField
    -0.42
     apresentam
    -0.41
     show
    -0.39
     J
    -0.38
     Gesam
    -0.38
    辞
    -0.38
     family
    -0.38
    ји
    -0.38
    CLC
    -0.38
    POSITIVE LOGITS
     صوتيه
    0.95
    ChildScrollView
    0.79
    WithMany
    0.76
     mergeFrom
    0.72
     ModelExpression
    0.69
    出版年
    0.67
    ]--;
    0.64
     "..\..\
    0.64
     '\\;'
    0.63
    RenderAtEndOf
    0.63
    Activations Density 0.979%

    No Known Activations