© 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. 35-GEMMASCOPE-RES-16K
    6. 6760
    Prev
    Next
    INDEX
    Explanations

    references to threats or curses related to power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.64
    expandindo
    -0.61
     prepping
    -0.60
     referenties
    -0.58
    Diweddarwch
    -0.58
    المكان
    -0.57
    PerformLayout
    -0.55
     πως
    -0.54
    Espèce
    -0.53
     whilst
    -0.51
    POSITIVE LOGITS
     ſol
    0.61
     ſur
    0.61
     élas
    0.60
     ſtre
    0.58
     ſal
    0.56
     tranſ
    0.56
     juſ
    0.55
     ſta
    0.54
     ſte
    0.53
     abſ
    0.53
    Activations Density 0.213%

    No Known Activations