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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14829
    Prev
    Next
    INDEX
    Explanations

    negative or contradictory sentiments expressed in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.92
     باخ
    -0.83
     ͡°
    -0.76
     transfieras
    -0.75
    ثة
    -0.71
    bolistas
    -0.68
     незавершена
    -0.67
     autorytatywna
    -0.67
    tagHelperRunner
    -0.66
     wtf
    -0.63
    POSITIVE LOGITS
     Okay
    0.96
     And
    0.95
     Um
    0.95
     okay
    0.90
    Okay
    0.85
     Yeah
    0.83
     um
    0.83
     Alright
    0.82
    Um
    0.79
     So
    0.78
    Activations Density 0.086%

    No Known Activations