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. 21-GEMMASCOPE-RES-16K
    6. 8493
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their concentrations in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.59
    IBOutlet
    -0.50
    createServer
    -0.46
    urably
    -0.45
    ondale
    -0.43
    ">//
    -0.43
    corer
    -0.41
    photobucket
    -0.41
     Sleeps
    -0.40
    RTCK
    -0.40
    POSITIVE LOGITS
     concentration
    1.38
     solution
    1.23
     Concentration
    1.21
     concentrations
    1.19
    concentration
    1.18
     solutions
    1.15
    Concentration
    1.14
     Concentrations
    1.08
     diluted
    1.07
     CONCENT
    1.06
    Activations Density 1.391%

    No Known Activations