© 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. 23-GEMMASCOPE-RES-16K
    11. 14514
    Prev
    Next
    INDEX
    Explanations

    references to harmful consequences or medical conditions related to substance use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imageshack
    -0.56
     يتيمه
    -0.49
     beginnetje
    -0.49
    uxxxx
    -0.46
    ubereitung
    -0.45
    oa̍t
    -0.44
    szönöm
    -0.44
    іе
    -0.44
    kano
    -0.44
     testGet
    -0.43
    POSITIVE LOGITS
     this
    3.54
    this
    3.37
    This
    2.12
     THIS
    2.04
    THIS
    1.96
     This
    1.92
     questo
    1.85
     questa
    1.83
     dieses
    1.79
     này
    1.79
    Activations Density 0.135%

    No Known Activations