© 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. 10092
    Prev
    Next
    INDEX
    Explanations

    terms related to the release of content or updates

    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
    AttributeSet
    -0.60
    Кру
    -0.52
    neighbor
    -0.51
     Entfernung
    -0.49
     "..\..\..\
    -0.49
    AndEndTag
    -0.49
    ξύ
    -0.48
     "..\..\
    -0.48
     Spazier
    -0.48
    leng
    -0.47
    POSITIVE LOGITS
    routeProvider
    0.75
     onCreateView
    0.69
    enterOuterAlt
    0.66
     unharmed
    0.64
    }],
    
    0.64
    HasAnnotation
    0.63
    原始内容存档于
    0.62
    VIAF
    0.62
     pent
    0.61
    اتها
    0.61
    Activations Density 0.124%

    No Known Activations