Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14709
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to infections and their effects on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.72
    }}}}
    -0.68
    })$}
    -0.64
    +");
    -0.60
    DoubleQuotes
    -0.60
    "]];
    -0.59
     []:
    -0.58
    čov
    -0.58
     })}
    -0.58
    +",
    -0.57
    POSITIVE LOGITS
     or
    0.54
    temos
    0.52
    anskje
    0.51
    enumi
    0.51
    DataAnnotations
    0.49
     semplicemente
    0.48
     simply
    0.48
     eller
    0.47
     Pourtant
    0.46
     вроде
    0.46
    Activations Density 0.578%

    No Known Activations