© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13044
    Prev
    Next
    INDEX
    Explanations

    phrases related to treatment protocols and clinical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विश्वसनीयता
    -0.55
    MessageOf
    -0.54
    HostException
    -0.53
    URLException
    -0.49
    
    -0.49
     ***!
    -0.48
     surla
    -0.47
    outWeight
    -0.46
    resaid
    -0.45
    hilangan
    -0.45
    POSITIVE LOGITS
     rather
    0.42
     plutôt
    0.40
     piuttosto
    0.39
    XmlEnum
    0.37
     OGSÅ
    0.36
    彿
    0.35
     acá
    0.35
    abstract
    0.32
     NCC
    0.31
     נד
    0.31
    Activations Density 0.804%

    No Known Activations