© 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. 5-GEMMASCOPE-RES-16K
    6. 6444
    Prev
    Next
    INDEX
    Explanations

    formatted textual elements, such as italicized or bolded text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -1.55
    </strong>
    -1.52
    <em>
    -1.28
    <strong>
    -1.23
     fl
    -1.23
    ",@"
    -1.14
    fl
    -1.11
     
    -1.03
     يتيمه
    -1.02
     first
    -1.02
    POSITIVE LOGITS
    </b>
    2.07
    </i>
    1.90
    <i>
    1.36
    dfrac
    1.18
    <b>
    1.15
    </td>
    0.93
    '''
    0.93
     ± 
    0.88
    َّ
    0.87
     Prussian
    0.86
    Activations Density 0.038%

    No Known Activations