© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 64956
    Prev
    Next
    INDEX
    Explanations

    C-style programming language constructs and syntax, particularly associated with function definitions and control structures

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

    C++ macros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.84
     initComponents
    -0.80
    aarrggbb
    -0.77
    CppCodeGen
    -0.74
    RenderAtEndOf
    -0.73
    ReusableCell
    -0.73
    SBATCH
    -0.73
    abestanden
    -0.73
    SharedDtor
    -0.72
     <<<<<<<<<<<<<<
    -0.68
    POSITIVE LOGITS
    }}}
    
    0.50
    }}
    
    0.43
    }*/
    
    0.40
    "];
    
    0.39
    ']);
    
    0.38
    ()]);
    0.38
    "]);
    
    0.36
    });
    
    0.36
    }),
    
    0.36
    }));
    
    0.36
    Activations Density 0.034%

    No Known Activations