© 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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3887
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols involving functions and their derivatives in a statistical or econometric context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ExtendWith
    -0.60
    .*")]
    -0.57
     CreateTagHelper
    -0.56
    makeConstraints
    -0.55
    ()));
    
    -0.54
    IntoConstraints
    -0.54
     betweenstory
    -0.52
    "]];
    -0.51
     ]]
    -0.50
     ]);
    -0.50
    POSITIVE LOGITS
    }
    0.69
    }\
    0.65
    },
    0.63
    }.
    0.59
    };
    0.57
    }
    
    0.56
    }:
    0.54
    }>
    0.52
    }'
    0.49
    }=
    0.48
    Activations Density 0.778%

    No Known Activations