© 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. 4-GEMMASCOPE-RES-16K
    6. 525
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in XML layout attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    )')
    -0.74
    ')));
    -0.73
    ()]);
    -0.71
    .))
    -0.71
    ")));
    
    -0.71
     */
    
    
    -0.69
    }';
    -0.69
    >');
    -0.68
    ."),
    -0.68
    POSITIVE LOGITS
    _
    1.67
    \_
    0.99
     _
    0.76
    __
    0.73
    _{
    0.68
    _\
    0.64
    ___
    0.63
     linkovi
    0.61
    }_
    0.61
    CloseOperation
    0.59
    Activations Density 0.339%

    No Known Activations