© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8886
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations relevant to probability and statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Probability, especially with mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    Prob }}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.81
    <b>
    -0.66
    }}}}
    -0.64
     ]
    -0.62
    <u>
    -0.60
    <strong>
    -0.59
     }}}
    -0.58
    havi
    -0.56
    )))))
    -0.56
     "
    -0.55
    POSITIVE LOGITS
    ftagPool
    1.09
    存于互联网档案馆
    1.01
     مشين
    1.01
    endphp
    1.01
     noqa
    0.97
    parsedMessage
    0.96
    Personensuche
    0.90
    сылкі
    0.87
    󠁮
    0.87
     متعلقه
    0.86
    Activations Density 0.710%

    No Known Activations