© 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. 18-GEMMASCOPE-RES-16K
    6. 2648
    Prev
    Next
    INDEX
    Explanations

    references to authorship and the rights associated with creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "do" or "does"

    np_acts-logits-general · gemini-2.0-flash

    you do/does/did

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.86
     GenerationType
    -0.80
     Monfieur
    -0.79
    NUMX
    -0.78
    "):
    
    -0.78
     transférez
    -0.77
     Jefus
    -0.77
    )");
    
    -0.76
     Efq
    -0.76
    IUrlHelper
    -0.75
    POSITIVE LOGITS
     did
    1.48
     does
    1.45
     do
    1.31
    did
    1.22
    does
    1.19
     hacerlo
    1.14
    Does
    1.11
    Did
    1.11
     Did
    1.10
     Does
    1.08
    Activations Density 0.444%

    No Known Activations