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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11433
    Prev
    Next
    INDEX
    Explanations

    terms related to biological activity and conditions affecting enzyme or patient treatment responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.52
     surla
    -0.49
    VYMaps
    -0.48
    期刊论文
    -0.45
    clusal
    -0.43
    ScopeManager
    -0.43
    UnknownFieldSet
    -0.42
    konomi
    -0.38
     يتيمه
    -0.38
     betweenstory
    -0.36
    POSITIVE LOGITS
     relating
    0.60
     pertaining
    0.58
     autorytatywna
    0.57
     involving
    0.54
     galore
    0.52
     related
    0.52
     representing
    0.52
     commemorating
    0.51
     consisting
    0.51
     of
    0.50
    Activations Density 2.116%

    No Known Activations