© 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. 24-GEMMASCOPE-RES-16K
    6. 5781
    Prev
    Next
    INDEX
    Explanations

    themes of personal struggle and emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    specific items or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.50
     unique
    -0.46
     higher
    -0.44
     Morin
    -0.44
     Gans
    -0.44
     major
    -0.43
     utilize
    -0.43
     beacon
    -0.43
     Lein
    -0.43
     Higher
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.63
    
    0.58
    SequentialGroup
    0.54
    حوالہ
    0.53
    EndContext
    0.53
     <<<<<<<<<<<<<<
    0.52
    IUrlHelper
    0.52
     étrangère
    0.51
    ंदीखरीदारी
    0.50
     ujednoznacz
    0.50
    Activations Density 0.474%

    No Known Activations