© 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. 21-GEMMASCOPE-RES-16K
    6. 14834
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to layout and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.84
    ]));
    
    -0.82
    >*/
    -0.79
    principalColumn
    -0.79
    __":
    -0.77
    __':
    -0.77
    RegressionTest
    -0.75
    ⓧ
    -0.75
    __':
    
    -0.75
    ()',
    -0.75
    POSITIVE LOGITS
     !
    0.81
    !
    0.75
    ;
    0.64
     !!
    0.56
    !!
    0.51
     !!!
    0.51
    !
    0.49
    !!!
    0.46
    px
    0.42
    AndEndTag
    0.40
    Activations Density 0.045%

    No Known Activations