Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7893
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotions related to challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     muß
    -0.72
     daß
    -0.60
     Moslem
    -0.55
     läßt
    -0.54
     quelquefois
    -0.54
    faßt
    -0.50
     occorre
    -0.50
     Надо
    -0.50
    ieważ
    -0.50
    parms
    -0.50
    POSITIVE LOGITS
     entirety
    0.84
     incentiv
    0.82
    Alright
    0.82
    Woah
    0.80
    Anyways
    0.78
     schonmal
    0.78
     Anyways
    0.77
     anyways
    0.77
     overarching
    0.75
     advancements
    0.73
    Activations Density 4.821%

    No Known Activations