© 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. 10-GEMMASCOPE-RES-16K
    6. 12947
    Prev
    Next
    INDEX
    Explanations

    references and figures within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.77
    principalTable
    -0.72
     resourceCulture
    -0.61
     }?>
    -0.59
    ########.
    -0.58
     }}}
    -0.56
    AsUp
    -0.55
     economica
    -0.54
    esterday
    -0.53
    WebServlet
    -0.53
    POSITIVE LOGITS
    BeginContext
    0.56
    otro
    0.54
    oa̍t
    0.49
    iastes
    0.48
    QUART
    0.48
    fitriones
    0.47
    writers
    0.47
    WriteAttribute
    0.47
     insuffisamment
    0.46
    WillAppear
    0.46
    Activations Density 1.325%

    No Known Activations