© 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. 2-GEMMASCOPE-RES-16K
    6. 5971
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operators related to probability and statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _\
    -0.67
     Brennan
    -0.57
    él
    -0.56
    AVEL
    -0.56
    oole
    -0.56
    伏
    -0.55
     Rod
    -0.55
    +(\
    -0.54
    REDIT
    -0.54
    mans
    -0.54
    POSITIVE LOGITS
    }_{\
    1.84
    }_{
    1.61
    }}_{\
    1.09
    }_
    1.07
     }_{\
    1.03
     }_{
    0.99
    }^{
    0.96
    }}_{
    0.96
    }_{+
    0.95
    }_{-
    0.94
    Activations Density 0.291%

    No Known Activations