© 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. 12606
    Prev
    Next
    INDEX
    Explanations

    elements of data structure or programming syntax

    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
    DoubleQuotes
    -0.58
    GraphicsUnit
    -0.58
    #+#
    -0.57
    +#+#
    -0.55
    ("")]
    
    -0.54
    ValueStyle
    -0.53
    MessageTagHelper
    -0.51
    hesion
    -0.51
    Бахар
    -0.50
    ="{{
    -0.50
    POSITIVE LOGITS
    بوابة
    0.60
     MainAxisSize
    0.58
    testens
    0.55
    czegó
    0.54
    nador
    0.53
    NSIndexPath
    0.51
     Chapter
    0.50
    Chapter
    0.50
    MethodImpl
    0.49
     Ode
    0.49
    Activations Density 0.708%

    No Known Activations