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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14018
    Prev
    Next
    INDEX
    Explanations

    advocacy and arguments related to social justice and rights

    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
    hires
    -0.65
    rsiniz
    -0.57
     I
    -0.56
     einges
    -0.51
     ơn
    -0.51
    httpResponse
    -0.50
     
    -0.49
     Me
    -0.49
    花板
    -0.48
    rud
    -0.48
    POSITIVE LOGITS
     advocating
    1.27
     Advoc
    1.23
     advocacy
    1.22
     défend
    1.17
     advocate
    1.15
    Advoc
    1.15
     advocated
    1.14
     argues
    1.14
    advoc
    1.13
     advocates
    1.13
    Activations Density 0.285%

    No Known Activations