© 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. 25-GEMMASCOPE-RES-16K
    6. 798
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </u>
    -0.65
    ”]
    -0.63
     --}}
    -0.61
     ?>
    
    -0.59
    Rohy
    -0.58
     ?></
    -0.58
    })*/
    -0.56
    uality
    -0.55
     }>
    -0.55
     */}
    -0.55
    POSITIVE LOGITS
    jamientos
    0.58
     Référence
    0.55
    numerusform
    0.51
    DispatchToProps
    0.49
    mặt
    0.46
     szóci
    0.46
    since
    0.45
     Babys
    0.44
    Personendaten
    0.43
    ToDate
    0.43
    Activations Density 0.022%

    No Known Activations