© 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. 23-GEMMASCOPE-RES-16K
    6. 6605
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to capacitors and circuits

    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
    MethodManager
    -0.67
     Audiodateien
    -0.57
    μένες
    -0.54
     Sust
    -0.51
     Kategor
    -0.50
    explique
    -0.50
    HomeAsUpEnabled
    -0.49
    setPower
    -0.49
     Merdeka
    -0.49
    velopes
    -0.48
    POSITIVE LOGITS
     resistance
    1.18
     Resistance
    1.06
    Resistance
    1.05
     RESISTANCE
    0.99
     Resist
    0.97
    resistance
    0.96
     resistances
    0.95
    Resist
    0.94
     capacitance
    0.93
     résistance
    0.88
    Activations Density 0.407%

    No Known Activations