© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12486
    Prev
    Next
    INDEX
    Explanations

    topics related to political issues and public policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gató
    -0.42
     desee
    -0.40
     nemmeno
    -0.38
     major
    -0.37
     much
    -0.37
     suerte
    -0.36
     Sam
    -0.36
     fermés
    -0.36
    ًا
    -0.36
     (
    -0.36
    POSITIVE LOGITS
     Мексичка
    1.13
    )++;
    0.96
     poffe
    0.89
     myſelf
    0.87
     raiſ
    0.87
    +#+#
    0.87
     neceff
    0.86
     houſe
    0.85
     pleaſure
    0.85
     ſever
    0.82
    Activations Density 1.890%

    No Known Activations