© 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. 11-GEMMASCOPE-RES-16K
    6. 4549
    Prev
    Next
    INDEX
    Explanations

    negations or prohibitive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sardinia
    -0.75
     ricardo
    -0.69
     PIB
    -0.67
     Coss
    -0.67
     ſever
    -0.66
     fevere
    -0.65
     Tübingen
    -0.65
     Clima
    -0.64
    τσα
    -0.64
     pleaſure
    -0.63
    POSITIVE LOGITS
     Not
    1.23
     NOT
    1.14
     not
    1.04
    Not
    0.98
     Normdatei
    0.96
    not
    0.94
    NOT
    0.94
    isNot
    0.92
    AddTagHelper
    0.92
     <=",
    0.89
    Activations Density 0.287%

    No Known Activations